Cropping Pattern Mapping in an Agro-Natural HeterogeneousLandscape Using Sentinel-2 and Sentinel-1 Satellite Datasets

Abstract

Abstract:The quantity of land covered by various crops in a specific time span, referred to as acropping pattern, dictates the level of agricultural production. However, retrieval of this informationat a landscape scale can be challenging, especially when high spatial resolution imagery is notavailable. This study hypothesized that utilizing the unique advantages of multi-date and mediumspatial resolution freely available Sentinel-2 (S2) reflectance bands (S2 bands), their vegetation indices(VIs) and vegetation phenology (VP) derivatives, and Sentinel-1 (S1) backscatter data would improvecropping pattern mapping in heterogeneous landscapes using robust machine learning algorithms,i.e., the guided regularized random forest (GRRF) for variable selection and the random forest (RF)for classification. This study’s objective was to map cropping patterns within three sub-counties inMurang’a County, a typical African smallholder heterogeneous farming area, in Kenya. Specifically,the performance of eight classification scenarios for mapping cropping patterns was compared,namely: (i) only S2 bands; (ii) S2 bands and VIs; (iii) S2 bands and VP; (iv) S2 bands and S1; (v) S2bands, VIs, and S1; (vi) S2 bands, VP, and S1; (vii) S2 bands, VIs, and VP; and (viii) S2 bands, VIs, VP,and S1. Reference data of the dominant cropping patterns and non-croplands were collected. TheGRRF algorithm was used to select the optimum variables in each scenario, and the RF was used toperform the classification for each scenario. The highest overall accuracy was 94.33% with Kappaof 0.93, attained using the GRRF-selected variables of scenario (v) S2, VIs, and S1. Furthermore,McNemar’s test of significance did not show significant differences (p≤0.05) among the testedscenarios. This study demonstrated the strength of GRRF in selecting the most important variablesand the synergetic advantage of S2 and S1 derivatives to accurately map cropping patterns in small-scale farming-dominated landscapes. Consequently, the cropping pattern mapping approach can beused in other sites of relatively similar agro-ecological conditions. Additionally, these results can beused to understand the sustainability of food systems and to model the abundance and spread ofcrop insect pests, diseases, and pollinators