Gunther Schorcht

Per-field crop classification in irrigated agricultural regions in middle Asia using random forest and support vector machine ensemble

Accurate crop identification and crop area estimation are important for studies on irrigated agricultural systems, yield and water demand modeling, and agrarian policy development. In this study a novel combination of Random Forest (RF) and Support Vector Machine (SVM) classifiers is presented that (i) enhances crop classification accuracy and (ii) provides spatial information on map uncertainty. The methodology was implemented over four distinct irrigated sites in Middle Asia using RapidEye time series data. The RF feature importance statistics was used as feature-selection strategy for the SVM to assess possible negative effects on classification accuracy caused by an oversized feature space. The results of the individual RF and SVM classifications were combined with rules based on posterior classification probability and estimates of classification probability entropy. SVM classification performance was increased by feature selection through RF. Further experimental results indicate that the hybrid classifier improves overall classification accuracy in comparison to the single classifiers as well as user´s and producer´s accuracy.

Potentials of RapidEye time series for improved classification of crop rotations in heterogeneous agricultural landscapes: Experiences from irrigation systems in Central Asia

In Central Asia, more than eight Million ha of agricultural land are under irrigation. But severe degradation problems and unreliable water distribution have caused declining yields during the past decades. Reliable and area-wide information about crops can be seen as important step to elaborate options for sustainable land and water management. Experiences from RapidEye classifications of crop in Central Asia are exemplarily shown during a classification of eight crop classes including three rotations with winter wheat, cotton, rice, and fallow land in the Khorezm region of Uzbekistan covering 230,000 ha of irrigated land. A random forest generated by using 1215 field samples was applied to multitemporal RapidEye data acquired during the vegetation period 2010. But RapidEye coverage varied and did not allow for generating temporally consistent mosaics covering the entire region. To classify all 55,188 agricultural parcels in the region three classification zones were classified separately. The zoning allowed for including at least three observation periods into classification. Overall accuracy exceeded 85 % for all classification zones. Highest accuracies of 87.4 % were achieved by including five spatiotemporal composites of RapidEye. Class-wise accuracy assessments showed the usefulness of selecting time steps which represent relevant phenological phases of the vegetation period. The presented approach can support regional crop inventory. Accurate classification results in early stages of the cropping season permit recalculation of crop water demands and reallocation of irrigation water. The high temporal and spatial resolution of RapidEye can be concluded highly beneficial for agricultural land use classifications in entire Central Asia.

Assessing irrigated cropland dynamics in central Asia between 2000 and 2011 based on MODIS time series

Monitoring of vegetation dynamics in extensive irrigated croplands is essential for improving land and water management, especially to understand the reaction of the system to water scarcity and degradation processes. This study focuses on the assessment of irrigated cropland dynamics in the western part of the Aral Sea Basin in Central Asia during the past decade. Extend of cropland and spatio-temporal cropping patters are analyzed based on phenological profiles extracted from 16day MODIS vegetation index time series at a spatial resolution of 250m. Knowledge-based classifications which needed to be adjusted for every single year were applied to distinguish between cropland and other major land cover types, the desert or sparsely vegetated steppes, settled areas, and water bodies. Interannual variability of the time series in the maximum cropland extend recorded between 2001 and 2010 was assessed by using Pearson’s cross correlation (PCC) coefficient. Shifts of maximum one month (+/-) were tested and the highest PCC coefficient was selected. Accuracy assessment using a multi-annual MODIS classification conducted for a representative irrigation system between 2004 and 2007 returned acceptable results for the cropland mask (<90%). Comparing the inter-annual cropland dynamics revealed using PCC with both, the MODIS classifications 2004-2007 and pure pixels of aggregated ASTER based maps showed that the PCC only permits differentiation between different modalities in the time series, i.e. years of a varying number of intra-annual crop cycles. However, simply overlaying the cropland extends 2001-2010 already exhibits areas of unreliable water supply. In this light, integration of both, PCC analysis of MODIS time series and annual maps of the cropland extent can be concluded as valuable next steps for better understanding the dynamics of the irrigated cropland at regional scale not only in the Aral Sea Basin of Central Asia, but also in other arid environments, where irrigation agriculture is essential for rural income generation and food security.

Crop classification at subfield level using RapidEye time series and graph theory algorithms

Accurate information about land use patterns is crucial for a sustainable and economical use of water in agricultural systems. Water demand estimation, yield modeling and agrarian policy are only a few applications addressed by land use classifications based on remote sensing imagery. In Central Asia, where fields are traditionally large and state order crops dominate the area, small units of fields are often separated for the additional cultivation of income crops for the farmers. Traditional object based land use classifications on multi-temporal satellite imagery using field boundaries show low classification accuracies on these separated fields, expressed by a high uncertainty of the final class labels. Although segmentation of smaller subfields was shown to be suitable for improving the classification result, the extraction of subfields is still a time-consuming and error-prone process. In this study, energy based Graph-Cut segmentation technique is used to enhance the segmentation process and finally to improve the classification result. The interactive segmentation technique was successfully adopted from bio-medical image analysis to fit remote sensing imagery in the spatial and in the temporal domain. A set of rules was developed to perform the image segmentation procedure on pixels of single satellite datasets and on objects representing time series of a vegetation index. An ensemble classifier based on Random Forest and Support Vector Machines was used to receive information about classification uncertainty before and after applying the segmentation. It is demonstrated that subfield extraction based on Graph Cuts outperforms traditional image segmentation approaches in simplicity and reduces the risk of under- and over-segmentation significantly. Classification uncertainty decreased using the derived subfields as object boundaries instead of original field boundaries. The segmentation technique performs well on several multi-temporal satellite images without changing parameters and may be used to refine object based land use classifications to subfield level.

A re-examination of perpendicular drought indices over Central and Southwest Asia

Drought monitoring models and products assist decision makers in drought planning, preparation, and mitigation, all of which can play a role in reducing drought impacts. In this study, the performance of two newly developed remote sensing-based drought indices, the perpendicular drought index (PDI) and modified perpendicular drought index (MPDI), are further explored for regional drought monitoring in agricultural regions located in central and south western Asia. The study area covers regions from moderate and wet climatological zones with dense vegetation coverage to semi-arid and arid climatological conditions with moderate to poor vegetation coverage. The spatio-temporal patterns of surface drought derived by PDI and MPDI from 250m MODerate Resolution Imaging Spectroradiometer (MODIS) data in 8-day time steps are compared against two other drought indices: the Standardized Precipitation Index (SPI) as a meteorological drought index and the potential evapotranspiration (ET0) as an agro-meteorological drought index, which both were calculated based on field-measured precipitation and regional meteorological parameters. In addition, 8-day MODIS Normalized Difference Vegetation Index (NDVI) was calculated and its performance to detect drought occurrence and measuring of drought severity compared with the two perpendicular drought indices. Significant correlations were found between the PDI, the MPDI and precipitation and other applied meteorological and agrometeorological drought indices. The results confirm previous studies which has been analyzing the PDI and the MPDI over some study points in Iran. In this research, however, implementation of higher resolution data (MOD09Q1) in both spatial (250 m) and temporal (8-days) dimensions revealed a greater agreement between the drought information extracted by the MPDI, PDI and field meteorological measurements. It could be concluded that the applied perpendicular indices could be used as a drought early warning system over case study region and other regions with similar arid and semi-arid climatological conditions.