Maize Cropping Systems Mapping Using RapidEye Observations in Agro-Ecological Landscapes in Kenya.

Kyalo Richard,Hosein Jozani,Sevgan Subramanian,Tobias Landmann,Johnson O Nyasani,Michael Thiel,Christian Borgemeister,Elfatih M Abdel-Rahman

doi:10.3390/s17112537

Abstract

Cropping systems information on explicit scales is an important but rarely available variable in many crops modeling routines and of utmost importance for understanding pests and disease propagation mechanisms in agro-ecological landscapes. In this study, high spatial and temporal resolution RapidEye bio-temporal data were utilized within a novel 2-step hierarchical random forest (RF) classification approach to map areas of mono- and mixed maize cropping systems. A small-scale maize farming site in Machakos County, Kenya was used as a study site. Within the study site, field data was collected during the satellite acquisition period on general land use/land cover (LULC) and the two cropping systems. Firstly, non-cropland areas were masked out from other land use/land cover using the LULC mapping result. Subsequently an optimized RF model was applied to the cropland layer to map the two cropping systems (2nd classification step). An overall accuracy of 93% was attained for the LULC classification, while the class accuracies (PA: producer’s accuracy and UA: user’s accuracy) for the two cropping systems were consistently above 85%. We concluded that explicit mapping of different cropping systems is feasible in complex and highly fragmented agro-ecological landscapes if high resolution and multi-temporal satellite data such as 5 m RapidEye data is employed. Further research is needed on the feasibility of using freely available 10–20 m Sentinel-2 data for wide-area assessment of cropping systems as an important variable in numerous crop productivity models.

Highlights

Agro-ecological systems in Africa are vulnerable to climate variability and climate change due to their over dependence on rainfall [1]
For classifying the the combined with ntree value of resulted in the lowest error rate of for classifying the monomixed maize cropping systemsas asshown shown (Figure monoand and mixed maize cropping systems (Figure3b)
The classification results from this study demonstrated the usefulness of the bi-temporal RapidEye imagery and random forest (RF) classification tool for mapping the two major maize cropping systems in heterogeneous agro-ecological landscapes

Summary

Introduction

Agro-ecological systems in Africa are vulnerable to climate variability and climate change due to their over dependence on rainfall [1]. While information about cropland extents or crop acreages is increasingly available and being used in food supply projections [3], explicit information about the actual cropping systems is not largely utilized or available. This leads to significant uncertainties in crop production models and in food security projections for Africa [4]. The cropping system is defined as the planting sequence of crops applied to an agricultural area or field over a certain period. We define mixed cropping as maize grown in a spatial arrangement with other leguminous crops on the same field within the same growing season and mono-cropping as maize grown as a single crop within the same time frame and field

Objectives

Methods

Results

Discussion

Conclusion