High Resolution, Annual Maps of Field Boundaries for Smallholder-Dominated Croplands at National Scales

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.

Location, biophysical and agronomic parameters for croplands in Northern Ghana

“…The data sets collected in 2020 and 2021 can be used to extend previous efforts to provide cropland/crop type maps (Xiong et al, 2017;Jolivot et al, 2021;Estes et al, 2021;Burton et al, 2022), but here we illustrate the use of the 2021 data set in developing a 10 m maize mask for the whole Northern province in Ghana using data from Sentinel 2. The classification experiment is done using the Google Earth Engine platform (Gorelick et al, 2017).…”

“…As more of these data sets become available (e.g. Estes et al (2021)), the data we provided in this contribution can be used as a source of independent validation, but also as a source…”

“…To be able to estimate total production or even average productivity in some region, an additional level of sophistication is needed on top of that where the crop type is identified. While there have been some recent advances on cropland masks derived from Earth Observation for the region (Burton et al, 2022;Estes et al, 2021;Xiong et al, 2017), accurate, timely data sets that allow the location of individual crops over large areas are still mainly lacking.…”

Location, biophysical and agronomic parameters for croplands in northern Ghana

“…The data sets collected in 2020 and 2021 can be used to extend previous efforts to provide cropland/crop-type maps (Xiong et al, 2017;Jolivot et al, 2021;Estes et al, 2022;Burton et al, 2022), but here we illustrate the use of the 2021 data set in developing a 10 m maize mask for the whole Northern zone in Ghana using data from Sentinel 2. The classification experiment is done using the Google Earth Engine platform (Gorelick et al, 2017).…”

“…To be able to estimate total production or even average productivity in some region, an additional level of sophistication is needed on top of that where the crop type is identified. While there have been some recent advances in cropland masks derived from Earth observation for the region (Burton et al, 2022;Estes et al, 2022;Xiong et al, 2017), accurate, timely data sets that allow the location of individual crops over large areas are still mainly lacking.…”