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.
ABSTRACT
The southern Yucatán contains the largest expanse of seasonal tropical forests remaining in Mexico, forming an ecocline between the drier north of the peninsula and the humid Petén, Guatemala. The Calakmul Biosphere Reserve resides in the center of this region as part of the Mesoamerican Biological Corridor. The reserve's functions are examined in regard to land changes throughout the region, generated over the last 40 years by increasing settlement and the expansion and intensification of agriculture. These changes are documented from 1987/1988 to 2000, and their implications regarding the capacity of the reserve to protect the ecocline, forest habitats, and butterfly diversity are addressed. The results indicate that the current landscape matrix serves the biotic diversity of the reserve, with several looming caveats involving the loss of humid forests and the interruption of biota flow across the ecocline, and the amount and proximity of older forest patches beyond the reserve. The highly dynamic land cover changes underway in this economic frontier warrant an adaptive management approach that monitors the major changes underway in mature forest types, while the paucity of systematic ecological and environment-development studies is rectified in order to inform policy and practice.
