Crop mapping in West Africa is challenging, due to the unavailability of adequate satellite images (as a result of excessive cloud cover), small agricultural fields and a heterogeneous landscape. To address this challenge, we integrated high spatial resolution multi-temporal optical (RapidEye) and dual polarized (VV/VH) SAR (TerraSAR-X) data to map crops and crop groups in northwestern Benin using the random forest classification algorithm. The overall goal was to ascertain the contribution of the SAR data to crop mapping in the region. A per-pixel classification result was overlaid with vector field boundaries derived from image segmentation, and a crop type was determined for each field based on the modal class within the field. A per-field accuracy assessment was conducted by comparing the final classification result with reference data derived from a field campaign. Results indicate that the integration of RapidEye and TerraSAR-X data improved classification accuracy by 10%–15% over the use of RapidEye only. The VV polarization was found to better discriminate crop types than the VH polarization. The research has shown that if optical and SAR data are available for the whole cropping season, classification accuracies of up to 75% are achievable.

The overarching goal of this research was to explore accurate methods of mapping irrigated crops, where digital cadastre information is unavailable: (a) Boundary separation by object-oriented image segmentation using very high spatial resolution (2.5–5 m) data was followed by (b) identification of crops and crop rotations by means of phenology, tasselled cap, and rule-based classification using high resolution (15–30 m) bi-temporal data. The extensive irrigated cotton production system of the Khorezm province in Uzbekistan, Central Asia, was selected as a study region. Image segmentation was carried out on pan-sharpened SPOT data. Varying combinations of segmentation parameters (shape, compactness, and color) were tested for optimized boundary separation. The resulting geometry was validated against polygons digitized from the data and cadastre maps, analysing similarity (size, shape) and congruence. The parameters shape and compactness were decisive for segmentation accuracy. Differences between crop phenologies were analyzed at field level using bi-temporal ASTER data. A rule set based on the tasselled cap indices greenness and brightness allowed for classifying crop rotations of cotton, winter-wheat and rice, resulting in an overall accuracy of 80 %. The proposed field-based crop classification method can be an important tool for use in water demand estimations, crop yield simulations, or economic models in agricultural systems similar to Khorezm.

Crop type classification using Earth Observation (EO) data is challenging, particularly for crop types with similar phenological growth stages. In this regard, the synergy of optical and Synthetic-Aperture Radar (SAR) data enables a broad representation of biophysical and structural information on target objects, enhancing crop type mapping. However, the fusion of multi-sensor dense time-series data often comes with the challenge of high dimensional feature space. In this study, we (1) evaluate how the usage of only optical, only SAR, and their fusion affect the classification accuracy; (2) identify the combination of which time-steps and feature-sets lead to peak accuracy; (3) analyze misclassifications based on the parcel size, optical data availability, and crops’ temporal profiles. Two fusion approaches were considered and compared in this study: feature stacking and decision fusion. To distinguish the most relevant feature subsets time- and variable-wise, grouped forward feature selection (gFFS) was used. gFFS allows focusing analysis and interpretation on feature sets of interest like spectral bands, vegetation indices (VIs), or data sensing time rather than on single features. This feature selection strategy leads to better interpretability of results while substantially reducing computational expenses. The results showed that, in contrast to most other studies, SAR datasets outperform optical datasets. Similar to most other studies, the optical-SAR combination outperformed single sensor predictions. No significant difference was recorded between feature stacking and decision fusion. Random Forest (RF) appears to be robust to high feature space dimensionality. The feature selection did not improve the accuracies even for the optical-SAR feature stack with 320 features. Nevertheless, the combination of RF feature importance and time- and variable-wise gFFS rankings in one visualization enhances interpretability and understanding of the features’ relevance for specific classification tasks. For example, by enabling the identification of features that have high RF feature importance values but are, in their information content, correlated with other features. This study contributes to the growing domain of interpretable machine learning.