Field-Level Crop Type Classification with k Nearest Neighbors: A Baseline for a New Kenya Smallholder Dataset

Accurate crop type maps provide critical information for ensuring food security, yet there has been limited research on crop type classification for smallholder agriculture, particularly in sub-Saharan Africa where risk of food insecurity is highest. Publicly-available ground-truth data such as the newly-released training dataset of crop types in Kenya (Radiant MLHub) are catalyzing this research, but it is important to understand the context of when, where, and how these datasets were obtained when evaluating classification performance and using them as a benchmark across methods. In this paper, we provide context for the new western Kenya dataset which was collected during an atypical 2019 main growing season and demonstrate classification accuracy up to 64% for maize and 70% for cassava using k Nearest Neighbors--a fast, interpretable, and scalable method that can serve as a baseline for future work.

[1]  David B. Lobell,et al.  Smallholder maize area and yield mapping at national scales with Google Earth Engine , 2019, Remote Sensing of Environment.

[2]  Heather McNairn,et al.  A Review of Multitemporal Synthetic Aperture Radar (SAR) for Crop Monitoring , 2016 .

[3]  C. Justice,et al.  Strengthening agricultural decisions in countries at risk of food insecurity: The GEOGLAM Crop Monitor for Early Warning , 2016, Remote Sensing of Environment.

[4]  Stéphane Dupuy,et al.  A Combined Random Forest and OBIA Classification Scheme for Mapping Smallholder Agriculture at Different Nomenclature Levels Using Multisource Data (Simulated Sentinel-2 Time Series, VHRS and DEM) , 2017, Remote. Sens..

[5]  Thomas Seidl,et al.  k-Nearest Neighbor Classification , 2009, Encyclopedia of Database Systems.

[6]  Emma Izquierdo-Verdiguier,et al.  A Cloud-Based Multi-Temporal Ensemble Classifier to Map Smallholder Farming Systems , 2018, Remote. Sens..

[7]  Siobhan Murray,et al.  Eyes in the Sky, Boots on the Ground: Assessing Satellite- and Ground-Based Approaches to Crop Yield Measurement and Analysis in Uganda , 2018 .

[8]  Xavier Blaes,et al.  Estimating smallholder crops production at village level from Sentinel-2 time series in Mali's cotton belt , 2018, Remote Sensing of Environment.

[9]  S. Fritz,et al.  Comparison of global and regional land cover maps with statistical information for the agricultural domain in Africa , 2010 .

[10]  Jin Chen,et al.  A simple method for reconstructing a high-quality NDVI time-series data set based on the Savitzky-Golay filter , 2004 .

[11]  Stefano Ermon,et al.  Semantic Segmentation of Crop Type in Africa: A Novel Dataset and Analysis of Deep Learning Methods , 2019, CVPR Workshops.