Papers by Boudewijn van Leeuwen
Tájökológiai lapok, Dec 20, 2023
Összefoglalás: Az inváziós fajok komoly és gyakran visszafordíthatatlan károkat okoznak a biodive... more Összefoglalás: Az inváziós fajok komoly és gyakran visszafordíthatatlan károkat okoznak a biodiverzitásban és az ökoszisztéma szolgáltatásokban, amelyek alapvető fontosággal bírnak az ember fennmaradása szempontjából, emellett pollenjeik miatt népegészségügyi szempontból is fontos problémát jelenthetnek. Mind az ellenük való védekezés, mind az általuk okozott gazdasági és természetvédelmi károk világszerte óriási költségeket emésztenek fel. Hatékony kezelésükhöz ismernünk kell az inváziós fajok jelenlegi elterjedését, terjedésük dinamikáját, ökoszisztémákra, élőhelyekre és a gazdaságra gyakorolt pontos hatásukat. Napjainkban ezeknek az információknak nagy területekről való begyűjtése leghatékonyabban drónokkal (UAV -unmanned aerial vehicle) történő monitorozással lehetséges. A természetközeli gyepek jelentős biológiai sokféleséggel rendelkeznek és fontos ökoszisztéma szolgáltatásokat nyújtanak, azonban ezek az élőhelyek is ki vannak téve az inváziós fajok károkozásának. Magyarország Pannon homoki gyepjeit számos inváziós faj terjedése fenyegeti. Ezek közül a közönséges selyemkóró (Asclepias syriaca L.) térképezésével és monitorozásával foglalkoztunk, mivel az egyik leggyakoribb és legveszélyesebb inváziósfaj a Dél-Alföldi régióban. Mivel az inváziós növényfajok természetvédelmi kezelése a mezőgazdasági gyomszabályozás szemléletén és módszerein alapszik, így jelen tanulmány a mezőgazdaságban használt monitorozási eljárások átültetésének egy lehetséges módszertani fejlesztéseként értékelhető. Célunk volt megvizsgálni, hogy a precíziós mezőgazdaságban használt vegetációs indexek alkalmasak-e a közönséges selyemkóró egyed szintű azonosítására, állománynagyságának a meghatározására. Kutatásaink során UAV-val készült légifelvételekből (RGB és CIR) képzett vegetációs indexek (TGI, VARI, NDVI és SAVI) vizsgálatát végeztük el. A közönséges selyemkóró drónnal végzett állomány felmérését, térképezését a Kiskunsági Nemzeti Park Kolon-tó törzsterületéhez kapcsolódó két regenerálódó parlagon végeztük el, 2020 júliusában. Eredményeink szerint a selyemkóró hajtásainak és egyed szintű azonosításának a legalkalmasabb indexe a TGI volt. Az NDVI és SAVI indexek a selyemkóró területi lefedettségének (borításának) és tőszámának meghatározására kevésbé voltak alkalmasak mint a TGI, ugyanakkor alkalmasak lehetnek természetvédelmi kezelések hatékonyságának meghatározására. Eredményeink egyszerű, gyors, költséghatékony és minimális zavarást okozó módszert biztosítanak az inváziós faj nagykiterjedésű állományainak térképezéséhez, időben többször megismételt monitorozásához. Ezáltal a természetvédelem számára olyan információkat nyújthat, amelyek egyrészt az invázió elleni védekezés pontos megtervezését, másrészt a kezelések hatékonyságának ellenőrzését és nyomon követését is lehetővé teszi a jövőben. A műre a Creative Commons4.0 standard licenc alábbi típusa vonatkozik: CC-BY-NC-ND-4.0.
Journal of Environmental Geography, Jul 1, 2008
In recent times Artificial Neural Networks (ANNs) are more and more widely applied. The ANN is an... more In recent times Artificial Neural Networks (ANNs) are more and more widely applied. The ANN is an information processing system consisting of numerous simple processing units (neurons) that are arranged in layers and have weighted connections to each other. In the present study the possible application of an unsupervised neural network model, the self-organizing map (SOM), for the delineation of excess water areas have been examined. By means of the self-organizing map high-dimensional data of large databases could be mapped to a lowdimensional data space. Within a data set, it is able to develop homogeneous clusters, thus it can be effectively applied for the classification of multispectral satellite images. The classification was carried out for an area of 88 km 2 to the south of Hódmezővásárhely situated in the southeastern part of Hungary, which is frequently inundated by excess water. As input data, the intensity values of the pixels measured in six bands of a Landsat ETM image taken on 23rd April 2000 were used. To perform the classification, three different sized neural network models were created, which classified the pixels of the satellite image to 9, 12 and 16 clusters. By using the gained clusters three thematic maps were created, on which different types of excess water areas were delineated. During the validation of the results it was concluded that the applied neural network model is suitable for the delimitation of excess water areas and it could be an alternative to the traditional classification methods.
Journal of Environmental Geography, Jul 1, 2008
Since February 2008, an advanced system has been developed to acquire digital images in the visib... more Since February 2008, an advanced system has been developed to acquire digital images in the visible to near infrared wavelengths. Using this system, it is possible to acquire data for a large variety of applications. The core of the system consists of a Duncantech MS3100 CIR (Color-InfraRed) multispectral camera. The main advantages of the system are its affordability and flexibility; within an hour the system can be deployed against very competitive costs. In several steps, using ArcGIS, Python and Avenue scripts, the raw data is semi-automatically processed into geo-referenced mosaics. This paper presents the parts of the system, the image processing workflow and several potential applications of the images.
The processing of HRIT wavelet compressed data, received at ITC with a standard size dish, is dis... more The processing of HRIT wavelet compressed data, received at ITC with a standard size dish, is discussed. Specifically a 14 day full disk image time series was generated with the aim of producing a data set of the Iberian Peninsula to support the ESA/SPARC 2004 field campaign. Software was developed for the efficient extraction of a image time series, which is both geocoded and radiometrically corrected. Improvements to the SEVIRI processing toolbox are discussed. To be able to generate Land Surface Temperatures, simple atmospheric corrections are being developed, using split window techniques and fast approximations to MODTRAN. Finally, total ozone content is determined through application of the method by Drouin and Karcher, with the use of p-T atmospheric profiles from the ECMWF (MARS) archives and MODIS level 2 products. MSG-1 Hotb ird 6 EUMETCAST Receiving System Satellite dish on roof of ITC Storage MSG-1 MSG-1 Hotb ird 6 Hotb ird 6 EUMETCAST Receiving System Satellite dish on roof of ITC Storage Receiving System Satellite dish on roof of ITC Storage
Journal of Environmental Geography, Nov 1, 2017
Inland excess water (IEW) is a type of flood where large flat inland areas are covered with water... more Inland excess water (IEW) is a type of flood where large flat inland areas are covered with water during a period of several weeks to months. The monitoring of these floods is needed to understand the extent and direction of development of the inundations and to mitigate their damage to the agricultural sector and build up infrastructure. Since IEW affects large areas, remote sensing data and methods are promising technologies to map these floods. This study presents the first results of a system that can monitor inland excess water over a large area with sufficient detail at a high interval and in a timely matter. The methodology is developed in such a way that only freely available satellite imagery is required and a map with known water bodies is needed to train the method to identify inundations. Minimal human interference is needed to generate the IEW maps. We will present a method describing three parallel workflows, each generating separate maps. The maps are combined to one weekly IEW map. At this moment, the method is capable of generating IEW maps for a region of over 8000 km 2 , but it will be extended to cover the whole Great Hungarian Plain, and in the future, it can be extended to any area where a training water map can be created.
Journal of Environmental Geography, Jun 1, 2016
The most obvious characteristics of urban climate are higher air and surface temperatures compare... more The most obvious characteristics of urban climate are higher air and surface temperatures compared to rural areas and large spatial variation of meteorological parameters within the city. This research examines the long term and seasonal development of urban surface temperature using satellite data during a period of 30 years and within a year. The medium resolution Landsat data were (pre)processed using open source tools. Besides the analysis of the long term and seasonal changes in land surface temperature within a city, also its relationship with changes in the vegetation cover was investigated. Different urban districts and local climate zones showed varying strength of correlation. The temperature difference between urban surfaces and surroundings is defined as surface urban heat island (SUHI). Its development shows remarkable seasonal and spatial anomalies. The satellite images can be applied to visualize and analyze the SUHI, although they were not collected at midday and early afternoon, when the phenomenon is normally at its maximum. The applied methodology is based on free data and software and requires minimal user interaction. Using the results new urban developments (new built up and green areas) can be planned, that help mitigate the negative effects of urban climate.
Journal of Environmental Geography, Apr 1, 2021
Agricultural production in greenhouses shows a rapid growth in many parts of the world. This form... more Agricultural production in greenhouses shows a rapid growth in many parts of the world. This form of intensive farming requires a large amount of water and fertilizers, and can have a severe impact on the environment. The number of greenhouses and their location is important for applications like spatial planning, environmental protection, agricultural statistics and taxation. Therefore, with this study we aim to develop a methodology to detect plastic greenhouses in remote sensing data using machine learning algorithms. This research presents the results of the use of a convolutional neural network for automatic object detection of plastic greenhouses in high resolution remotely sensed data within a GIS environment with a graphical interface to advanced algorithms. The convolutional neural network is trained with manually digitized greenhouses and RGB images downloaded from Google Earth. The ArcGIS Pro geographic information system provides access to many of the most advanced python-based machine learning environments like Keras-TensorFlow, PyTorch, fastai and Scikit-learn. These libraries can be accessed via a graphical interface within the GIS environment. Our research evaluated the results of training and inference of three different convolutional neural networks. Experiments were executed with many settings for the backbone models and hyperparameters. The performance of the three models in terms of detection accuracy and time required for training was compared. The model based on the VGG_11 backbone model (with dropout) resulted in an average accuracy of 79.2% with a relatively short training time of 90 minutes, the much more complex DenseNet121 model was trained in 16.5 hours and showed a result of 79.1%, while the ResNet18 based model showed an average accuracy of 83.1% with a training time of 3.5 hours.
Journal of Applied Remote Sensing, 2011
Many places in the world show spectacular landscape changes caused by increasingly rapid alterati... more Many places in the world show spectacular landscape changes caused by increasingly rapid alterations of natural phenomena observed in the last 3 to 4 decades. More and more studies reveal the consequences of global climate change strengthened by anthropogenic ...
Sustainability, Apr 3, 2020
Changing climate is expected to cause more extreme weather patterns in many parts of the world. I... more Changing climate is expected to cause more extreme weather patterns in many parts of the world. In the Carpathian Basin, it is expected that the frequency of intensive precipitation will increase causing inland excess water (IEW) in parts of the plains more frequently, while currently the phenomenon already causes great damage. This research presents and validates a new methodology to determine the extent of these floods using a combination of passive and active remote sensing data. The method can be used to monitor IEW over large areas in a fully automated way based on freely available Sentinel-1 and Sentinel-2 remote sensing imagery. The method is validated for two IEW periods in 2016 and 2018 using high-resolution optical satellite data and aerial photographs. Compared to earlier remote sensing data-based methods, our method can be applied under unfavorite weather conditions, does not need human interaction and gives accurate results for inundations larger than 1000 m 2. The overall accuracy of the classification exceeds 99%; however, smaller IEW patches are underestimated due to the spatial resolution of the input data. Knowledge on the location and duration of the inundations helps to take operational measures against the water but is also required to determine the possibilities for storage of water for dry periods. The frequent monitoring of the floods supports sustainable water management in the area better than the methods currently employed.
^ `ab `a[c d e aY \d fbab`g ae abh dbig Y Zbjdbâe e Zc c dc abhk ]dY dl ZY dk ĝ g c g jmZŶ ab^ Ẑ ... more ^ `ab `a[c d e aY \d fbab`g ae abh dbig Y Zbjdbâe e Zc c dc abhk ]dY dl ZY dk ĝ g c g jmZŶ ab^ Ẑ jĝ g \ad ĝ c `Zbc dn[db`dc o p]d m]dbZe Z\q m]ac dc Zl id\dâĝ Zb aY d ĉ Y Zb\e q g br[db`dh sq hY Z[\]ô p]g c Y dc daỲ] hdcY g sdc a tZY urZt Ẑ dĉ g jad m]dbZe Z\q abh mY Zh[`ĝ iĝ q maY ajddY c sac dh Zb jdhg [j Y dc Ze [ĝ Zb c ade e ĝ d haâo vg Y ĉ k ]d ammY ZmY g ad jd]Zhc l ZY fê dY g b\ Zl id\dâĝ Zb haâ abh \dbdY ae g waĝ Zb Zl ]d AQ+/
REGIONÁLIS LÉPTÉKŰ aSzÁLymONITORINGOT TÁmOGaTó vEGETÁcIó-ÉS TaLajNEdvESSÉG ÉRTÉKELÉS mOdIS adaTOK... more REGIONÁLIS LÉPTÉKŰ aSzÁLymONITORINGOT TÁmOGaTó vEGETÁcIó-ÉS TaLajNEdvESSÉG ÉRTÉKELÉS mOdIS adaTOK aLaPjÁN Kovács Ferenc-van Leeuwen Boudewijn-Ladányi ZsuZsanna-raKoncZai jános-GuLácsi andrás veGeTaTion and soiL MoisTure assessMenTs Based on Modis daTa To suPPorT reGionaL drouGHT MoniTorinG abstract climate models predict a combined trend of higher average temperatures and less precipitation for the carpathian Basin. This makes the region vulnerable to future droughts. droughts are complex phenomena that require large amounts of data to study them. Point measurements acquired by measurement stations provide accurate data with high temporal resolution, but for a limited number of locations. satellite data can be used to complement point measurements to extend the amount of information available for drought studies. This research presents three methods to study drought at regional scale based on medium resolution satellite data. we determined that satellite based indices (ddi, nddi) show a strong correlation coefficient with a drought index (Pai) based on meteorological data. Furthermore, we show that evi based vegetation productivity has a strong relationship with the severity of drought. Finally, we show that medium resolution satellite data can be used to estimate soil moisture content.
Land, Dec 22, 2022
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
Journal of Environmental Geography, Apr 1, 2020
Classification of multispectral optical satellite data using machine learning techniques to deriv... more Classification of multispectral optical satellite data using machine learning techniques to derive land use/land cover thematic data is important for many applications. Comparing the latest algorithms, our research aims to determine the best option to classify land use/land cover with special focus on temporary inundated land in a flat area in the south of Hungary. These inundations disrupt agricultural practices and can cause large financial loss. Sentinel 2 data with a high temporal and medium spatial resolution is classified using open source implementations of a random forest, support vector machine and an artificial neural network. Each classification model is applied to the same data set and the results are compared qualitatively and quantitatively. The accuracy of the results is high for all methods and does not show large overall differences. A quantitative spatial comparison demonstrates that the neural network gives the best results, but that all models are strongly influenced by atmospheric disturbances in the image.
Drones
Today, invasive alien species cause serious trouble for biodiversity and ecosystem services, whic... more Today, invasive alien species cause serious trouble for biodiversity and ecosystem services, which are essential for human survival. In order to effectively manage invasive species, it is important to know their current distribution and the dynamics of their spread. Unmanned aerial vehicle (UAV) monitoring is one of the best tools for gathering this information from large areas. Vegetation indices for multispectral camera images are often used for this, but RGB colour-based vegetation indices can provide a simpler and less expensive solution. The goal was to examine whether six RGB indices are suitable for identifying invasive plant species in the QGIS environment on UAV images. To examine this, we determined the shoot area and number of common milkweed (Asclepias syriaca) and the inflorescence area and number of blanket flowers (Gaillardia pulchella) as two typical invasive species in open sandy grasslands. According to the results, the cover area of common milkweed was best identi...
Quarterly Journal of …, 2010
The aim of this study is to develop a new-and easy to use-method for early night-time near-surfac... more The aim of this study is to develop a new-and easy to use-method for early night-time near-surface air temperature pattern estimation based on surface temperature data in urban areas. The surface temperature data have been collected by an airborne thermal infrared sensor at an altitude of 2000 m above ground level. The study area was covered by hundreds of images with a spatial resolution of about 2 m. The measured values were calibrated with data of in situ surface measurements of different land use types. Simultaneous air temperature measurements were carried out using a carbased temperature sensor along an almost 12 km long N-S urban transect. The measured points were located using a GPS device. Data were processed with GIS methods, including newly developed algorithms. In order to find the relationship between air and surface temperatures a wider environment, the source area which determines the air temperature at a given point and time was taken into account. Using a source area with a radius of 500 m, a strong relationship was detected between the two parameters. Namely, the temperatures of the surfaces found in the surroundings (weighted by the distance) determine the temperature of the air parcel located at a given point. The obtained regression equation was applied to extend our results in order to model the air temperature field in a larger urban area.
Uploads
Papers by Boudewijn van Leeuwen