Geomatic Approaches for Modeling Land Change Scenarios, 2017
Validation is the third stage in the modeling process, after calibration and simulation, and also... more Validation is the third stage in the modeling process, after calibration and simulation, and also applies to scenarios. It is an essential part of the process in that the credibility of a model depends on the accuracy of its output. A large range of validation approaches and tools exist, many of which can also be used during the calibration stage. In this chapter we distinguish between purely quantitative validation techniques and those that also consider the spatial allocation of simulated land use/cover changes (LUCC). According to model outputs and objectives, simulation maps can be either hard-classified or soft-classified. While some validation techniques apply to both types of map (cross tabulation matrices and indices, congruence of model outputs), others are specific to one. Techniques such as LUCC indicators, feature and pattern recognition and error analysis are used to validate hard-classified simulation maps, while ROC is used to test soft-classified maps. We then look at a second validation approach based on LUCC dynamics such as LUCC components, intensity analysis, data uncertainty and the impact of spatial and temporal scales. Finally, we compare a group of the most common model software programs (those used by the contributors to parts II and III of this book), in order to list their validation capabilities.
In land change modeling, the simulation stage uses parameters and processes to allocate changes b... more In land change modeling, the simulation stage uses parameters and processes to allocate changes by resolving competition between transitions. They are also used to reproduce spatiotemporal patterns of modeled change. There are also several advanced options that try to improve the simulation outputs. This chapter focuses on these simulation steps and on the different types of simulated maps (soft and hard outputs). A theoretical presentation of concepts and methods for each simulation step and simulation output is followed by a comparative analysis of the different approaches for estimating the parameters for the most common pattern-based models (PBM) and constraint cellular automata-based models (CCAM).
Land change models can help scientists and users to understand change processes and design polici... more Land change models can help scientists and users to understand change processes and design policies to reduce the negative impact of human activities on the earth system at scales ranging from global to local. With the development of increasingly large computing capacities, multiple computer-based models have been created, with the result that the specific domain covered by the umbrella term “modeling” has become rather vague. Even within the context of the spatiotemporal modeling of land use and cover changes (LUCC), the term “modeling” can have many different meanings. There is also an increasing interest in the literature in comparing the different land change models. One of the aims of this book is to contribute to these processes. We focus on geomatic modeling approaches applied in this context to land change, a term that has been used synonymously for a number of years with LUCC and seems to be overtaking it as the generally used term for this phenomenon. The objective of this...
Geomatic Approaches for Modeling Land Change Scenarios, 2017
In land change modeling, calibration enables the modeler to establish the parameters for the mode... more In land change modeling, calibration enables the modeler to establish the parameters for the model in order to produce expected outcomes, similar to those observed for the study area over a period in the past or consistent with a given scenario. Depending on the modeling approach, the parameters are set using maps which describe past change or information obtained from experts or stakeholders. These parameters will control the behavior of the model during the simulation with regard to aspects such as the quantity and the spatiotemporal patterns of modeled change. This chapter focuses on different aspects of calibration, such as the selection and transformation of input variables and the different approaches for estimating the parameters of the most common pattern-based models (PBM) and constraint cellular automata-based models (CCAM).
IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477)
Presents a procedure for mapping land use/cover combining the spectral information from a recent ... more Presents a procedure for mapping land use/cover combining the spectral information from a recent image and data about spatial distribution of land use/cover types obtained from outdated cartography and ancillary data. Two fuzzy maps, which indicate the membership of each land use/cover class, were generated from the ancillary and spectral data, respectively, using an artificial neural networks approach. The combination of both maps was obtained using fuzzy rules. In comparison with spectral classification, this procedure allowed improving the accuracy of land use/cover classification from 67% to 79%.
Sentinel-2 imagery has the highest temporal, spectral and spatial resolution to monitor land surf... more Sentinel-2 imagery has the highest temporal, spectral and spatial resolution to monitor land surface among the freely available multispectral collections. However, the possibility to use these images in different applications is conditioned by the number of cloudless observations available for a certain spatiotemporal window. Thus, the objective of this article is to analyze the number of Sentinel-2 observations available for the Mexican territory at image and pixel level. In the first case, the total number of available images and its cloud cover percentage was calculated; while in the second case, the number of cloudless observations was estimated for each pixel. Additionally, in order to take into account the territory diversity, the monthly mean number of cloudless observations, as well as the proportion of its surface with at least one cloudless observation in monthly, bimonthly, trimonthly and annual intervals, was computed for each one of the seven ecoregions of the country. ...
ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2015
This article presents a hybrid method that combines image segmentation, GIS analysis, and visual ... more This article presents a hybrid method that combines image segmentation, GIS analysis, and visual interpretation in order to detect discrepancies between an existing land use/cover map and satellite images, and assess land use/cover changes. It was applied to the elaboration of a multidate land use/cover database of the State of Michoacán, Mexico using SPOT and Landsat imagery. The method was first applied to improve the resolution of an existing 1:250,000 land use/cover map produced through the visual interpretation of 2007 SPOT images. A segmentation of the 2007 SPOT images was carried out to create spectrally homogeneous objects with a minimum area of two hectares. Through an overlay operation with the outdated map, each segment receives the “majority” category from the map. Furthermore, spectral indices of the SPOT image were calculated for each band and each segment; therefore, each segment was characterized from the images (spectral indices) and the map (class label). In order ...
ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2015
Spatially explicit land use / land cover (LUCC) models aim at simulating the patterns of change o... more Spatially explicit land use / land cover (LUCC) models aim at simulating the patterns of change on the landscape. In order to simulate landscape structure, the simulation procedures of most computational LUCC models use a cellular automata to replicate the land use / cover patches. Generally, model evaluation is based on assessing the location of the simulated changes in comparison to the true locations but landscapes metrics can also be used to assess landscape structure. As model complexity increases, the need to improve calibration and assessment techniques also increases. In this study, we applied a genetic algorithm tool to optimize cellular automata’s parameters to simulate deforestation in a region of the Brazilian Amazon. We found that the genetic algorithm was able to calibrate the model to simulate more realistic landscape in term of connectivity. Results show also that more realistic simulated landscapes are often obtained at the expense of the location coincidence. Howev...
... Une revue des méthodes et des techniques. ... 81-86. Crósta, AP, Roig, HL, Elvidge, CD, 1995,... more ... Une revue des méthodes et des techniques. ... 81-86. Crósta, AP, Roig, HL, Elvidge, CD, 1995, Multitemporal Image Analysis Applied to Environmental Monitoring in the Brazilian Amazon,Memorias del VII Simposio Latinoamericano de Percepción Remota, Puerto Vallarta Nov. ...
ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2016
Anthropogenic land-cover change, e.g. deforestation and forest degradation cause carbon emissions... more Anthropogenic land-cover change, e.g. deforestation and forest degradation cause carbon emissions. To estimate deforestation and forest degradation, it is important to have reliable data on forest cover. In this analysis, we evaluated annual MODIS Percent Tree Cover (PTC) data for the detection of forest change including deforestation, forest degradation, reforestation and revegetation. The annual MODIS PTC data (2000 – 2010) were pre-processed by applying quality layer. Based on the PTC values of the annual MODIS data, forest change maps were produced and assessed by comparing with the data from visual interpretation of SPOT-5 images. The assessment was applied to two case-studies: Ayuquila Basin and Monarch Reserve. Results show that the detected deforestation patches by visual interpretation are roughly 4 times in quantity more than those by MODIS PTC data, which can be partially due to the much higher spatial resolution of SPOT-5, being able to pick up small deforestation patche...
In order to determine rates of deforestation in the State of Campeche, Mexico, forest maps of 197... more In order to determine rates of deforestation in the State of Campeche, Mexico, forest maps of 1978/80 and 1992 were compared within a geographic information system (GIS). Results indicate that more than 25 per cent of the tropical forest and mangroves were deforested and other 29 per cent were fragmented during this period. The rate of deforestation in the whole state is about 4.4 per cent per year, but the analysis showed that rates of deforestation are much higher in the coastal zone. For this reason an attempt was made to study deforestation patterns in the coastal zone. Data such as distance from roads and from settlements images were incorporated in the GIS data base and a model which represents influence of population on its environment was developed in order to establish the influence of socioeconomic factors on forest clearing. Results indicate that deforestation presents a higher correlation with levels of poverty and social abandonment than with demographic aspects.
In the last two decades, advances in computer technology, earth observation sensors and GIS scien... more In the last two decades, advances in computer technology, earth observation sensors and GIS science, led to the development of "Object-based Image Analysis (OBIA)" as an alternative to the traditional pixel-based image analysis method. It was recognized that traditional pixel-based image analysis is limited because of the following reasons: image pixels are not true geographical objects and the pixel topology is limited; pixel based image analysis largely neglects the spatial photo-interpretive elements such as texture, context, and shape; the increased variability implicit within high spatial resolution imagery confuses traditional pixel-based classifiers resulting in lower classification accuracies (Hay and Castilla 2006). Different from pixel-based method, OBIA works on (homogeneous) objects produced by image segmentation and more elements can be used in the classification. As an object is a group of pixels, object characteristics such as mean value, standard deviation, ratio, etc can be calculated; besides there are shape and texture features of the objects available which can be used to differentiate land cover classes with similar spectral information. These extra types of information give OBIA the potential to produce land cover thematic maps with higher accuracies than those produced by traditional pixel-based method. In this paper, we look at the performance of OBIA with different spatial resolution satellite images; comparing the classification results with those produced by the pixel-based method, we intend to find out how spatial resolution of satellite images influences the performance of OBIA. Experiment results showed that with the two sets of images of four different spatial resolutions, object based image analysis obtained higher accuracies than those of the pixel based one; with the increasing of the spatial resolution, the difference in accuracy values between object based and pixel based is decreasing. This paper showed that the object-based image analysis has advantage over the pixel-based one, and in accuracy rating, the advantage was better represented by higher spatial resolution satellite images.
A common problem when classifying remotely sensed images in order to map land use/cover is spectr... more A common problem when classifying remotely sensed images in order to map land use/cover is spectral confusion: different land use/cover classes present similar spectral signatures and are misclassified. This paper presents a procedure for mapping land use/ cover combining the spectral information from a recent image and data about spatial distribution of land use/cover types obtained from outdated cartography and ancillary data. Two fuzzy maps, which indicate the membership of each land use/cover class, were generated from the ancillary and spectral data, respectively, using an artificial neural networks approach. The combination of both maps was obtained using fuzzy rules. In comparison with spectral classification, this procedure allowed a statistically significant increase of accuracy of land use/cover classification (from 67% to 79%). The advantages of this procedure for combining spectral and ancillary data, with regard to others previously published in the literature, are that it allows one to take into account previous mapping efforts and to establish relationships between land use/cover and environmental variables specific to the mapped area.
In view of the exponential growth in the volume of data that is considered in intelligent decisio... more In view of the exponential growth in the volume of data that is considered in intelligent decision-making, hyperspectral remote sensing (HRS) has, without doubt, brought greater dominance over agricultural crops as it goes beyond the paradigm of little information being available about the targets. In this review of the state of the art of HRS, complementary views on the use of sensors and analytical techniques in agriculture over the last decade are grouped together. State-of-the-art technologies, and research trends associated with each level of data collection are cited. There is still a long way to go in the agricultural sciences; however, specialists in precision agriculture are devotees of the valuable insights offered with the increased availability of hyperspectral data. In this respect, this review is organised as follows: Section 1 helps the reader to contextualise and conceptualise the basics of remote sensing; the second section discusses the types of sensors and their resolutions; section 3 presents four subsections that show recent applications of these technologies according to their level of acquisition; finally, the fourth section offers the reader a discussion on the positive trends achieved in managing vegetation, soils and waterbodies over the last ten years, as well as the needs and challenges of the next decade.
Elsevier Perspectives in Ecology and Conservation, 2021
Forest regeneration at large-scales is one of the main paths to achieving the ongoing ambitious r... more Forest regeneration at large-scales is one of the main paths to achieving the ongoing ambitious restoration commitments. Thus, the identification of the main drivers of this process in agricultural landscapes is critical to understand the drivers determining restoration success. A growing number of studies have explored the biophysical and, less often, the socioeconomic drivers of forest regeneration using remote sensing approaches, but have not directly considered the influence of farmers’ decisions in spatial prediction models of forest regeneration. We explored the influence of biophysical and socioeconomic drivers on forest regeneration in a rural landscape of Southeastern Brazil, where native forest cover increased by 7.7%. We evaluated forest regeneration through the analysis of time series of multi-temporal satellite images and socioeconomic information obtained through a Social Survey with 47 landowners, using each farm as the study unit. Natural forest regeneration was mainly favored by lower land suitability for agriculture and higher proximity (lower distances) to forest remnants, as well by higher numbers of land-uses types in the farm and lower economic dependence of landowners from the farm income. Our results emphasize the importance of considering farmers’ decisions on predictive models of natural forest regeneration, which are critically needed to guide the implementation of large-scale forest restoration initiatives in agricultural landscapes.
Landsat imagery offers the most extended continuous land surface observation at 30 m spatial reso... more Landsat imagery offers the most extended continuous land surface observation at 30 m spatial resolution and is widely used in land change studies. On the other hand, the recent developments on big data, such as cloud computing, give new opportunities for carrying out satellite-based continuous land cover monitoring including land use/cover change and more subtle changes as forest degradation, agriculture intensification and vegetation phenological patterns alterations. However, in the range 0–10∘ south latitude, especially in the summer and autumn, there is a high rainfall and high clouds presence. We hypothesise that it will be challenging to characterise vegetation phenology in regions where the number of valid (cloud-free) remotely-sensed observation is low or when the observations are unevenly distributed over the year. This paper aims to evaluate whether there is sufficient availability of Landsat 7 and 8 images over Brazil to support the analysis of phenodynamics of vegetation. We used Google Earth Engine to assess Landsat data availability during the last decades over the Brazilian territory. The valid observations (excluding clouds and shadow areas) from Landsat 4/5/7/8 during the period 1984–2017 were determined at pixel level. The results show a lower intensity of Landsat observations in the northern and northeastern parts of Brazil compared to the southern region, mainly due to clouds’ presence. Taking advantage of the overlapping areas between satellite paths where the number of observations is larger, we modelled the loss of information caused by a lower number of valid (cloud free) observations. We showed that, in the deciduous woody formations of the Caatinga dominium, the scarcity of valid observations has an adverse effect on indices’ performance aimed at describing vegetation phenology. However, the combination of Landsat data with satellite constellation such as Sentinel will likely permit to overcome many of these limitations.
Geomatic Approaches for Modeling Land Change Scenarios, 2017
Validation is the third stage in the modeling process, after calibration and simulation, and also... more Validation is the third stage in the modeling process, after calibration and simulation, and also applies to scenarios. It is an essential part of the process in that the credibility of a model depends on the accuracy of its output. A large range of validation approaches and tools exist, many of which can also be used during the calibration stage. In this chapter we distinguish between purely quantitative validation techniques and those that also consider the spatial allocation of simulated land use/cover changes (LUCC). According to model outputs and objectives, simulation maps can be either hard-classified or soft-classified. While some validation techniques apply to both types of map (cross tabulation matrices and indices, congruence of model outputs), others are specific to one. Techniques such as LUCC indicators, feature and pattern recognition and error analysis are used to validate hard-classified simulation maps, while ROC is used to test soft-classified maps. We then look at a second validation approach based on LUCC dynamics such as LUCC components, intensity analysis, data uncertainty and the impact of spatial and temporal scales. Finally, we compare a group of the most common model software programs (those used by the contributors to parts II and III of this book), in order to list their validation capabilities.
In land change modeling, the simulation stage uses parameters and processes to allocate changes b... more In land change modeling, the simulation stage uses parameters and processes to allocate changes by resolving competition between transitions. They are also used to reproduce spatiotemporal patterns of modeled change. There are also several advanced options that try to improve the simulation outputs. This chapter focuses on these simulation steps and on the different types of simulated maps (soft and hard outputs). A theoretical presentation of concepts and methods for each simulation step and simulation output is followed by a comparative analysis of the different approaches for estimating the parameters for the most common pattern-based models (PBM) and constraint cellular automata-based models (CCAM).
Land change models can help scientists and users to understand change processes and design polici... more Land change models can help scientists and users to understand change processes and design policies to reduce the negative impact of human activities on the earth system at scales ranging from global to local. With the development of increasingly large computing capacities, multiple computer-based models have been created, with the result that the specific domain covered by the umbrella term “modeling” has become rather vague. Even within the context of the spatiotemporal modeling of land use and cover changes (LUCC), the term “modeling” can have many different meanings. There is also an increasing interest in the literature in comparing the different land change models. One of the aims of this book is to contribute to these processes. We focus on geomatic modeling approaches applied in this context to land change, a term that has been used synonymously for a number of years with LUCC and seems to be overtaking it as the generally used term for this phenomenon. The objective of this...
Geomatic Approaches for Modeling Land Change Scenarios, 2017
In land change modeling, calibration enables the modeler to establish the parameters for the mode... more In land change modeling, calibration enables the modeler to establish the parameters for the model in order to produce expected outcomes, similar to those observed for the study area over a period in the past or consistent with a given scenario. Depending on the modeling approach, the parameters are set using maps which describe past change or information obtained from experts or stakeholders. These parameters will control the behavior of the model during the simulation with regard to aspects such as the quantity and the spatiotemporal patterns of modeled change. This chapter focuses on different aspects of calibration, such as the selection and transformation of input variables and the different approaches for estimating the parameters of the most common pattern-based models (PBM) and constraint cellular automata-based models (CCAM).
IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477)
Presents a procedure for mapping land use/cover combining the spectral information from a recent ... more Presents a procedure for mapping land use/cover combining the spectral information from a recent image and data about spatial distribution of land use/cover types obtained from outdated cartography and ancillary data. Two fuzzy maps, which indicate the membership of each land use/cover class, were generated from the ancillary and spectral data, respectively, using an artificial neural networks approach. The combination of both maps was obtained using fuzzy rules. In comparison with spectral classification, this procedure allowed improving the accuracy of land use/cover classification from 67% to 79%.
Sentinel-2 imagery has the highest temporal, spectral and spatial resolution to monitor land surf... more Sentinel-2 imagery has the highest temporal, spectral and spatial resolution to monitor land surface among the freely available multispectral collections. However, the possibility to use these images in different applications is conditioned by the number of cloudless observations available for a certain spatiotemporal window. Thus, the objective of this article is to analyze the number of Sentinel-2 observations available for the Mexican territory at image and pixel level. In the first case, the total number of available images and its cloud cover percentage was calculated; while in the second case, the number of cloudless observations was estimated for each pixel. Additionally, in order to take into account the territory diversity, the monthly mean number of cloudless observations, as well as the proportion of its surface with at least one cloudless observation in monthly, bimonthly, trimonthly and annual intervals, was computed for each one of the seven ecoregions of the country. ...
ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2015
This article presents a hybrid method that combines image segmentation, GIS analysis, and visual ... more This article presents a hybrid method that combines image segmentation, GIS analysis, and visual interpretation in order to detect discrepancies between an existing land use/cover map and satellite images, and assess land use/cover changes. It was applied to the elaboration of a multidate land use/cover database of the State of Michoacán, Mexico using SPOT and Landsat imagery. The method was first applied to improve the resolution of an existing 1:250,000 land use/cover map produced through the visual interpretation of 2007 SPOT images. A segmentation of the 2007 SPOT images was carried out to create spectrally homogeneous objects with a minimum area of two hectares. Through an overlay operation with the outdated map, each segment receives the “majority” category from the map. Furthermore, spectral indices of the SPOT image were calculated for each band and each segment; therefore, each segment was characterized from the images (spectral indices) and the map (class label). In order ...
ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2015
Spatially explicit land use / land cover (LUCC) models aim at simulating the patterns of change o... more Spatially explicit land use / land cover (LUCC) models aim at simulating the patterns of change on the landscape. In order to simulate landscape structure, the simulation procedures of most computational LUCC models use a cellular automata to replicate the land use / cover patches. Generally, model evaluation is based on assessing the location of the simulated changes in comparison to the true locations but landscapes metrics can also be used to assess landscape structure. As model complexity increases, the need to improve calibration and assessment techniques also increases. In this study, we applied a genetic algorithm tool to optimize cellular automata’s parameters to simulate deforestation in a region of the Brazilian Amazon. We found that the genetic algorithm was able to calibrate the model to simulate more realistic landscape in term of connectivity. Results show also that more realistic simulated landscapes are often obtained at the expense of the location coincidence. Howev...
... Une revue des méthodes et des techniques. ... 81-86. Crósta, AP, Roig, HL, Elvidge, CD, 1995,... more ... Une revue des méthodes et des techniques. ... 81-86. Crósta, AP, Roig, HL, Elvidge, CD, 1995, Multitemporal Image Analysis Applied to Environmental Monitoring in the Brazilian Amazon,Memorias del VII Simposio Latinoamericano de Percepción Remota, Puerto Vallarta Nov. ...
ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2016
Anthropogenic land-cover change, e.g. deforestation and forest degradation cause carbon emissions... more Anthropogenic land-cover change, e.g. deforestation and forest degradation cause carbon emissions. To estimate deforestation and forest degradation, it is important to have reliable data on forest cover. In this analysis, we evaluated annual MODIS Percent Tree Cover (PTC) data for the detection of forest change including deforestation, forest degradation, reforestation and revegetation. The annual MODIS PTC data (2000 – 2010) were pre-processed by applying quality layer. Based on the PTC values of the annual MODIS data, forest change maps were produced and assessed by comparing with the data from visual interpretation of SPOT-5 images. The assessment was applied to two case-studies: Ayuquila Basin and Monarch Reserve. Results show that the detected deforestation patches by visual interpretation are roughly 4 times in quantity more than those by MODIS PTC data, which can be partially due to the much higher spatial resolution of SPOT-5, being able to pick up small deforestation patche...
In order to determine rates of deforestation in the State of Campeche, Mexico, forest maps of 197... more In order to determine rates of deforestation in the State of Campeche, Mexico, forest maps of 1978/80 and 1992 were compared within a geographic information system (GIS). Results indicate that more than 25 per cent of the tropical forest and mangroves were deforested and other 29 per cent were fragmented during this period. The rate of deforestation in the whole state is about 4.4 per cent per year, but the analysis showed that rates of deforestation are much higher in the coastal zone. For this reason an attempt was made to study deforestation patterns in the coastal zone. Data such as distance from roads and from settlements images were incorporated in the GIS data base and a model which represents influence of population on its environment was developed in order to establish the influence of socioeconomic factors on forest clearing. Results indicate that deforestation presents a higher correlation with levels of poverty and social abandonment than with demographic aspects.
In the last two decades, advances in computer technology, earth observation sensors and GIS scien... more In the last two decades, advances in computer technology, earth observation sensors and GIS science, led to the development of "Object-based Image Analysis (OBIA)" as an alternative to the traditional pixel-based image analysis method. It was recognized that traditional pixel-based image analysis is limited because of the following reasons: image pixels are not true geographical objects and the pixel topology is limited; pixel based image analysis largely neglects the spatial photo-interpretive elements such as texture, context, and shape; the increased variability implicit within high spatial resolution imagery confuses traditional pixel-based classifiers resulting in lower classification accuracies (Hay and Castilla 2006). Different from pixel-based method, OBIA works on (homogeneous) objects produced by image segmentation and more elements can be used in the classification. As an object is a group of pixels, object characteristics such as mean value, standard deviation, ratio, etc can be calculated; besides there are shape and texture features of the objects available which can be used to differentiate land cover classes with similar spectral information. These extra types of information give OBIA the potential to produce land cover thematic maps with higher accuracies than those produced by traditional pixel-based method. In this paper, we look at the performance of OBIA with different spatial resolution satellite images; comparing the classification results with those produced by the pixel-based method, we intend to find out how spatial resolution of satellite images influences the performance of OBIA. Experiment results showed that with the two sets of images of four different spatial resolutions, object based image analysis obtained higher accuracies than those of the pixel based one; with the increasing of the spatial resolution, the difference in accuracy values between object based and pixel based is decreasing. This paper showed that the object-based image analysis has advantage over the pixel-based one, and in accuracy rating, the advantage was better represented by higher spatial resolution satellite images.
A common problem when classifying remotely sensed images in order to map land use/cover is spectr... more A common problem when classifying remotely sensed images in order to map land use/cover is spectral confusion: different land use/cover classes present similar spectral signatures and are misclassified. This paper presents a procedure for mapping land use/ cover combining the spectral information from a recent image and data about spatial distribution of land use/cover types obtained from outdated cartography and ancillary data. Two fuzzy maps, which indicate the membership of each land use/cover class, were generated from the ancillary and spectral data, respectively, using an artificial neural networks approach. The combination of both maps was obtained using fuzzy rules. In comparison with spectral classification, this procedure allowed a statistically significant increase of accuracy of land use/cover classification (from 67% to 79%). The advantages of this procedure for combining spectral and ancillary data, with regard to others previously published in the literature, are that it allows one to take into account previous mapping efforts and to establish relationships between land use/cover and environmental variables specific to the mapped area.
In view of the exponential growth in the volume of data that is considered in intelligent decisio... more In view of the exponential growth in the volume of data that is considered in intelligent decision-making, hyperspectral remote sensing (HRS) has, without doubt, brought greater dominance over agricultural crops as it goes beyond the paradigm of little information being available about the targets. In this review of the state of the art of HRS, complementary views on the use of sensors and analytical techniques in agriculture over the last decade are grouped together. State-of-the-art technologies, and research trends associated with each level of data collection are cited. There is still a long way to go in the agricultural sciences; however, specialists in precision agriculture are devotees of the valuable insights offered with the increased availability of hyperspectral data. In this respect, this review is organised as follows: Section 1 helps the reader to contextualise and conceptualise the basics of remote sensing; the second section discusses the types of sensors and their resolutions; section 3 presents four subsections that show recent applications of these technologies according to their level of acquisition; finally, the fourth section offers the reader a discussion on the positive trends achieved in managing vegetation, soils and waterbodies over the last ten years, as well as the needs and challenges of the next decade.
Elsevier Perspectives in Ecology and Conservation, 2021
Forest regeneration at large-scales is one of the main paths to achieving the ongoing ambitious r... more Forest regeneration at large-scales is one of the main paths to achieving the ongoing ambitious restoration commitments. Thus, the identification of the main drivers of this process in agricultural landscapes is critical to understand the drivers determining restoration success. A growing number of studies have explored the biophysical and, less often, the socioeconomic drivers of forest regeneration using remote sensing approaches, but have not directly considered the influence of farmers’ decisions in spatial prediction models of forest regeneration. We explored the influence of biophysical and socioeconomic drivers on forest regeneration in a rural landscape of Southeastern Brazil, where native forest cover increased by 7.7%. We evaluated forest regeneration through the analysis of time series of multi-temporal satellite images and socioeconomic information obtained through a Social Survey with 47 landowners, using each farm as the study unit. Natural forest regeneration was mainly favored by lower land suitability for agriculture and higher proximity (lower distances) to forest remnants, as well by higher numbers of land-uses types in the farm and lower economic dependence of landowners from the farm income. Our results emphasize the importance of considering farmers’ decisions on predictive models of natural forest regeneration, which are critically needed to guide the implementation of large-scale forest restoration initiatives in agricultural landscapes.
Landsat imagery offers the most extended continuous land surface observation at 30 m spatial reso... more Landsat imagery offers the most extended continuous land surface observation at 30 m spatial resolution and is widely used in land change studies. On the other hand, the recent developments on big data, such as cloud computing, give new opportunities for carrying out satellite-based continuous land cover monitoring including land use/cover change and more subtle changes as forest degradation, agriculture intensification and vegetation phenological patterns alterations. However, in the range 0–10∘ south latitude, especially in the summer and autumn, there is a high rainfall and high clouds presence. We hypothesise that it will be challenging to characterise vegetation phenology in regions where the number of valid (cloud-free) remotely-sensed observation is low or when the observations are unevenly distributed over the year. This paper aims to evaluate whether there is sufficient availability of Landsat 7 and 8 images over Brazil to support the analysis of phenodynamics of vegetation. We used Google Earth Engine to assess Landsat data availability during the last decades over the Brazilian territory. The valid observations (excluding clouds and shadow areas) from Landsat 4/5/7/8 during the period 1984–2017 were determined at pixel level. The results show a lower intensity of Landsat observations in the northern and northeastern parts of Brazil compared to the southern region, mainly due to clouds’ presence. Taking advantage of the overlapping areas between satellite paths where the number of observations is larger, we modelled the loss of information caused by a lower number of valid (cloud free) observations. We showed that, in the deciduous woody formations of the Caatinga dominium, the scarcity of valid observations has an adverse effect on indices’ performance aimed at describing vegetation phenology. However, the combination of Landsat data with satellite constellation such as Sentinel will likely permit to overcome many of these limitations.
Gebhardt et al. (2014) presented the Monitoring Activity Data for the Mexican REDD+ program (MAD-... more Gebhardt et al. (2014) presented the Monitoring Activity Data for the Mexican REDD+ program (MAD-MEX), an automatic nationwide land cover monitoring system for the Mexican REDD+ MRV. Though MAD-MEX represents a valuable first effort toward establishing a national reference emissions level for the implementation of REDD+ in Mexico, in this paper, we argue that this land cover system has important limitations that may prevent it from becoming operational for REDD+ MRV. Specifically, we show that (1) the accuracy assessment of MAD-MEX land cover maps is optimistically biased; (2) the ability of MAD-MEX to monitor land cover change, including deforestation and forest degradation; is poor and (3) the use of an entirely automatic classification approach, such as that followed by MAD-MEX, is highly problematic in the case of a large and heterogeneous country like Mexico. We discuss these limitations and call into question the ability of a land cover monitoring system, such as MAD-MEX, both to elaborate a national reference emissions level and to monitor future forest cover change, as part of a REDD+ MRV system. We provide some insights with the aim of improving the development of nationwide land cover monitoring systems in Mexico and elsewhere.
Abstract: Spatially-explicit land cover land use change (LCLUC) models are becoming
increasingly ... more Abstract: Spatially-explicit land cover land use change (LCLUC) models are becoming increasingly useful tools for historians and archaeologists. Such kinds of models have been developed and used by geographers, ecologists and land managers over the last few decades to carry out prospective scenarios. In this paper, we review historical models to compare them with prospective models, with the assumption that the ample experience gained in the development of models of prospective simulation can benefit the development of models having as their objective the simulation of changes that happened in the past. The review is divided into three sections: in the first section, we explain the functioning of contemporary LCLUC models; in the second section, we analyze historical LCLUC models; in the third section, we compare the former two types of models, and finally, we discuss the contributions to historical LCLUC models of contemporary LCLUC models.
Durante os últimos anos, foram criados diferentes pacotes de R dirigidos à análise espacial. Aind... more Durante os últimos anos, foram criados diferentes pacotes de R dirigidos à análise espacial. Ainda assim, existem poucos livros focados na análise espacial com R . Este livro destina-se a usuários com conhecimento básico de Sistemas de Informação Geográfica (SIG) que desejam iniciar a gestão e análise de dados espaciais com R. Portanto, não requer nenhum conhecimento prévio deste programa, mas um conhecimento básico do SIG. O livro pretende permitir ao leitor dar os primeiros passos na gestão de R para a análise espacial sem muitos tropeços. No primeiro capítulo, é explicado como instalar R e RStudio e os principais elementos da interface RStudio são apresentados. É recomendado instalar ambos os programas para experimentar os códigos dos exercícios. No segundo capítulo, é feita uma introdução ao uso básico do R. O leitor com conhecimento prévio de R pode ir diretamente para o capítulo seguinte. No terceiro capítulo, apresentamos como os dados espaciais em R estão estruturados utilizando os pacotes sf e raster, os dois principais pacotes que usaremos ao longo deste livro. Este capítulo pode parecer um pouco árido. No capítulo 4, apresentamos algumas maneiras de interagir com dados geográficos entre R e outros sistemas de gerenciamento de informações geográficas através de procedimentos de importação / exportação de dados em formato vetorial ou de imagem, bem como alguns métodos para converter informações entre vetor e raster. Nos capítulos 5 e 6, são apresentadas operações SIG básicas, respectivamente, com dados em formato vetorial e raster. No Capítulo 7, apresentamos algumas análises do campo da geoestatística que podem ser realizadas com pacotes R. No oitavo capítulo mostramos algumas maneiras de elaborar cartografia. Finalmente, o capítulo 9 apresenta ao leitor as técnicas para fazer R interagir com o sistema de informação geográfica (SIG) de código aberto Q-GIS e a plataforma de modelagem espacial Dinamica EGO.
Gracias a diferentes módulos orientados al análisis espacial, R, una reconocida plataforma de aná... more Gracias a diferentes módulos orientados al análisis espacial, R, una reconocida plataforma de análisis estadístico es ahora una potente herramienta para llevar a cabo el mapeo y el análisis de todo tipo de información georeferenciada. El presente libro se dirige a usuarios con conocimiento básico de Sistemas de Información Geográfica (SIG) que desean iniciarse en el manejo y análisis de datos espaciales en R. No requiere por lo tanto de ningún conocimiento previo de este programa pero sí un conocimiento básico de los SIG. El libro pretende permitir al lector dar los primeros pasos en el manejo de R para el análisis espacial de forma amena. El libro está organizado en nueve capítulos e incluye códigos que el lector puede reproducir. En el primer capítulo, se explica cómo instalar R y RStudio y se presentan los principales elementos de la interface RStudio. En el segundo capítulo, se presenta una introducción al manejo básico de R. En el tercer capítulo, se presenta cómo están estructurados los datos espaciales en R en los paquetes sf y raster. En el capítulo 4, se presentan algunas formas para intercambiar datos geográficos entre R y otros sistemas de manejo de información geográfica a través de procedimientos de importación / exportación, así como algunos métodos para convertir información entre vector y raster. En los capítulos 5 y 6, se presentan operaciones básicas de SIG, respectivamente con datos en formato vector y raster. En el capítulo 7, se muestran algunos de los numerosos análisis geoestadísticos que se pueden llevar a cabo con paquetes de R. En el octavo capítulo, se aborda el análisis de imágenes de satélite. El capítulo 9 muestra algunas formas de elaborar cartografía. Finalmente, el décimo capítulo introduce al lector las técnicas para hacer interactuar R con el programa SIG de código abierto Q-GIS y la plataforma de modelación espacial Dinamica EGO.
Esta obra fue pensada como un foro de presentación de resultados de investigación para la generac... more Esta obra fue pensada como un foro de presentación de resultados de investigación para la generación de perspectivas novedosas y originales acerca de los problemas de cambio ambiental que enfrentan los países en Latinoamérica. Se abordan varios aspectos de la modelación espacial para el análisis de procesos medioambientales como la recuperación de la vegetación nativa, los cambios de cubierta / uso del suelo, con un énfasis especial en la deforestación, la pérdida de biodiversidad así como el efecto de políticas públicas.
Uploads
Papers by JF Mas
increasingly useful tools for historians and archaeologists. Such kinds of models have been
developed and used by geographers, ecologists and land managers over the last few decades
to carry out prospective scenarios. In this paper, we review historical models to compare
them with prospective models, with the assumption that the ample experience gained in the
development of models of prospective simulation can benefit the development of models
having as their objective the simulation of changes that happened in the past. The review is
divided into three sections: in the first section, we explain the functioning of contemporary
LCLUC models; in the second section, we analyze historical LCLUC models; in the third
section, we compare the former two types of models, and finally, we discuss the contributions
to historical LCLUC models of contemporary LCLUC models.
El presente libro se dirige a usuarios con conocimiento básico de Sistemas de Información Geográfica (SIG) que desean iniciarse en el manejo y análisis de datos espaciales en R. No requiere por lo tanto de ningún conocimiento previo de este programa pero sí un conocimiento básico de los SIG. El libro pretende permitir al lector dar los primeros pasos en el manejo de R para el análisis espacial de forma amena.
El libro está organizado en nueve capítulos e incluye códigos que el lector puede reproducir. En el primer capítulo, se explica cómo instalar R y RStudio y se presentan los principales elementos de la interface RStudio. En el segundo capítulo, se presenta una introducción al manejo básico de R. En el tercer capítulo, se presenta cómo están estructurados los datos espaciales en R en los paquetes sf y raster. En el capítulo 4, se presentan algunas formas para intercambiar datos geográficos entre R y otros sistemas de manejo de información geográfica a través de procedimientos de importación / exportación, así como algunos métodos para convertir información entre vector y raster. En los capítulos 5 y 6, se presentan operaciones básicas de SIG, respectivamente con datos en formato vector y raster. En el capítulo 7, se muestran algunos de los numerosos análisis geoestadísticos que se pueden llevar a cabo con paquetes de R. En el octavo capítulo, se aborda el análisis de imágenes de satélite. El capítulo 9 muestra algunas formas de elaborar cartografía. Finalmente, el décimo capítulo introduce al lector las técnicas para hacer interactuar R con el programa SIG de código abierto Q-GIS y la plataforma de modelación espacial Dinamica EGO.