A5091004151- Remote Sensing in Agriculture
- Land Use and Ecosystem Services
- Rangeland Management and Livestock Ecology
- Smart Agriculture and AI
- Remote-Sensing Image Classification
- Transboundary Water Resource Management
- Climate change impacts on agriculture
- Animal Diversity and Health Studies
- Remote Sensing and LiDAR Applications
- Remote Sensing and Land Use
- Engineering and Agricultural Innovations
- Spectroscopy and Chemometric Analyses
- Atmospheric and Environmental Gas Dynamics
- Soil and Environmental Studies
- Land Rights and Reforms
- Hydrology and Drought Analysis
- Soil Geostatistics and Mapping
- Soil erosion and sediment transport
- Flood Risk Assessment and Management
- Atmospheric chemistry and aerosols
- Climate variability and models
- Plant Water Relations and Carbon Dynamics
- Oil Spill Detection and Mitigation
- Groundwater and Isotope Geochemistry
- Water Quality and Pollution Assessment
Federal Office of Civil protection and Disaster Assistance
2023
University of Bonn
2016
University of Würzburg
2011-2015
Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR)
2013
Heidelberg University
2011
Cropland abandonment is globally widespread and has strong repercussions for regional food security the environment. Statistics suggest that one of hotspots abandoned cropland located in drylands Aral Sea Basin (ASB), which covers parts post-Soviet Central Asia, Afghanistan Iran. To date, exact spatial temporal extents remain unclear, hampers land-use planning. Abandoned land a potentially valuable resource alternative uses. Here, we mapped ASB with time series Normalized Difference...
Accurate classification and mapping of crops is essential for supporting sustainable land management. Such maps can be created based on satellite remote sensing; however, the selection input data optimal classifier algorithm still needs to addressed especially areas where field scarce. We exploited intra-annual variation temporal signatures remotely sensed observations used prior knowledge crop calendars development a two-step processing chain classification. First, Landsat-based time-series...
The past decades have seen an increasing demand for operational monitoring of crop conditions and food production at local to global scales. To properly use satellite Earth observation such agricultural monitoring, high temporal revisit frequency over vast geographic areas is necessary. However, this often limits the spatial resolution that can be used. challenge discriminating pixels correspond a particular type, prerequisite specific remains daunting when signal encoded in stems from...
Accurate and timely information on the global cropland extent is critical for food security monitoring, water management earth system modeling. Principally, it allows analyzing satellite image time-series to assess crop conditions permits isolation of agricultural component focus impacts various climatic scenarios. However, despite its importance, accurate spatial extent, mapping with remote sensing imagery remains a major challenge. Following an exhaustive identification collection existing...
Accurate quantification of land use/cover change (LULCC) is important for efficient environmental management, especially in regions that are extremely affected by climate variability and continuous population growth such as West Africa. In this context, accurate LULC classification statistically sound area estimates essential a better understanding LULCC processes. This study aimed at comparing mono-temporal multi-temporal classifications well their combination with ancillary data to...
The world is facing a looming scarcity of land necessary to secure the production agricultural commodities and experiencing competition from other uses [...]
The lack of sufficient ground truth data has always constrained supervised learning, thereby hindering the generation up-to-date satellite-derived thematic maps. This is all more true for those applications requiring frequent updates over large areas such as cropland mapping. Therefore, we present a method enabling automated production spatially consistent maps at national scale, based on spectral-temporal features and outdated land cover information. Following an unsupervised approach, this...
Accurate agricultural yield prediction is a fundamental tool for sustainable planning and to ensure food security in regions critically affected by climate change extreme weather events. Existing regression-based crop estimation approaches typically rely on specific set of predictor variables, but have not been compared systematically. This paper demonstrates compares the utilization combinatorial use three different sets object-based predictors sugarcane through monitoring platform...
In the context of growing populations and limited resources, sustainable intensification agricultural production is great importance to achieve food security. As need support management at a range spatial scales grows, decision-support tools appear increasingly important enable timely regular assessment over large areas identify priorities for improving crop in low-productivity regions. Understanding productivity patterns requires provision gapless, information about productivity. this...
This study is aimed at a better understanding of how upstream runoff formation affected the cropping intensity (CI: number harvests) in Aral Sea Basin (ASB) between 2000 and 2012. MODIS 250 m NDVI time series knowledge-based pixel masking that included settlement layers topography features enabled to map irrigated cropland extent (iCE). Random forest models supported classification vegetation phenology (CVP: winter/summer crops, double cropping, etc.). CI percentage fallow (PF) were derived...
Terrestrial oil spills are a major threat to environmental and human well-being. Rapid, accurate, remote spatial assessment of contamination is critical implementing countermeasures that prevent potentially lasting ecological damage irreversible harm local communities. Satellite sensing has been used support such assessments in inaccessible regions, although mapping small terrestrial challenging – partly due the pixel size systems, but also distinguishability spill areas from other land...
Mapping the spatial and temporal dynamics of cropland is an important prerequisite for regular crop condition monitoring, management land water resources, or tracing understanding environmental impacts agriculture. Analyzing archives satellite earth observations a proven means to accurately identify map croplands. However, existing maps annual extent either have low resolution (e.g., 250–1000 m from Advanced Very High Resolution Radiometer (AVHRR) Moderate-resolution Imaging...
The ground truth data sets required to train supervised classifiers are usually collected as maximize the number of samples under time, budget and accessibility constraints. Yet, performance machine learning is, among other factors, sensitive class proportions training set. In this letter, joint effect calibration on accuracy was systematically quantified using two state-of-the-art (random forests support vector machines). analysis applied in context binary cropland classification focused...
Accurate crop identification and area estimation are important for studies on irrigated agricultural systems, yield water demand modeling, agrarian policy development. In this study a novel combination of Random Forest (RF) Support Vector Machine (SVM) classifiers is presented that (i) enhances classification accuracy (ii) provides spatial information map uncertainty. The methodology was implemented over four distinct sites in Middle Asia using RapidEye time series data. RF feature...