High resolution, annual maps of field boundaries for smallholder-dominated croplands at national scales

This is a Preprint and has not been peer reviewed. This is version 4 of this Preprint.

Add a Comment

You must log in to post a comment.


Comments

There are no comments or no comments have been made public for this article.

Downloads

Download Preprint

Supplementary Files
Authors

Lyndon D Estes, Su Ye, Lei Song, Boka Luo, J. Ronald Eastman, Zhenhua Meng, Qi Zhang, Dennis McRitchie, Stephanie R. Debats, Justus Muhando, Angeline H. Amukoa, Brian W. Kaloo, Jackson Makuru, Ben K. Mbatia, Isaac M. Muasa, Julius Mucha, Adelide M. Mugami, Judith M. Mugami, Francis W. Muinde, Fredrick M. Mwawaza, Jeff Ochieng, Charles J. Oduol, Purent Oduor, Thuo Wanjiku, Joseph G. Wanyoike, Ryan Avery, Kelly Caylor

Abstract

Mapping the characteristics of Africa's smallholder-dominated croplands, including the sizes and numbers of fields, can provide critical insights into food security and a range of other socioeconomic and environmental concerns. However, accurately mapping these systems is difficult because there is 1) a spatial and temporal mismatch between satellite sensors and smallholder fields, and 2) a lack of high-quality labels needed to train and assess machine learning classifiers. We developed an approach designed to address these two problems, and used it to map Ghana’s croplands. To overcome the spatio-temporal mismatch, we converted daily, high resolution imagery into two cloud-free composites (the primary growing season and subsequent dry season) covering the 2018 agricultural year, providing a seasonal contrast that helps to improve classification accuracy. To address the problem of label availability, we created a platform that rigorously assesses and minimizes label error, and used it to iteratively train a Random Forests classifier with active learning, which identifies the most informative training sample based on prediction uncertainty. Minimizing label errors improved model F1 scores by up to 25%. Active learning increased F1 scores by an average of 9.1% between first and last training iterations, and 2.3% more than models trained with randomly selected labels. We used the resulting 3.7 m map of cropland probabilities within a segmentation algorithm to delineate crop field boundaries. Using an independent map reference sample (n=1,207), we found that the cropland probability and field boundary maps had respective overall accuracies of 88% and 86.7%, user’s accuracies for the cropland class of 61.2% and 78.9%, and producer’s accuracies of 67.3% and 58.2%. An unbiased area estimate calculated from the map reference sample indicates that cropland covers 17.1% (15.4-18.9%) of Ghana. Using the most accurate validation labels to correct for biases in the segmented field boundaries map, we estimated that the average size and total number of field in Ghana are 1.73 ha and 1,662,281, respectively. Our results demonstrate an adaptable and transferable approach for developing annual, country-scale maps of crop field boundaries, with several features that effectively mitigate the errors inherent in remote sensing of smallholder-dominated agriculture.

DOI

https://doi.org/10.31223/X56C83

Subjects

Agriculture, Environmental Monitoring, Environmental Sciences, Geographic Information Sciences, Geography, Life Sciences, Natural Resources and Conservation, Physical and Environmental Geography, Physical Sciences and Mathematics, Remote Sensing, Spatial Science, Sustainability

Keywords

machine learning, Africa, active learning, CubeSat, PlanetScope, smallholder, cropland, field size, consensus labels, Ghana

Dates

Published: 2021-03-12 16:05

Last Updated: 2021-10-11 16:42

Older Versions
License

CC BY Attribution 4.0 International

Additional Metadata

Conflict of interest statement:
None