National level satellite-based crop field inventories in smallholder landscapes
- URL: http://arxiv.org/abs/2507.10499v1
- Date: Mon, 14 Jul 2025 17:23:43 GMT
- Title: National level satellite-based crop field inventories in smallholder landscapes
- Authors: Philippe Rufin, Pauline Lucie Hammer, Leon-Friedrich Thomas, Sá Nogueira Lisboa, Natasha Ribeiro, Almeida Sitoe, Patrick Hostert, Patrick Meyfroidt,
- Abstract summary: We provide the first national-level dataset of 21 million individual fields for Mozambique.<n>Our maps separate active cropland from non-agricultural land use with an overall accuracy of 93%.<n>Field size in Mozambique is very low overall, with half of the fields being smaller than 0.16 ha, and 83% smaller than 0.5 ha.
- Score: 0.746823468023145
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: The design of science-based policies to improve the sustainability of smallholder agriculture is challenged by a limited understanding of fundamental system properties, such as the spatial distribution of active cropland and field size. We integrate very high spatial resolution (1.5 m) Earth observation data and deep transfer learning to derive crop field delineations in complex agricultural systems at the national scale, while maintaining minimum reference data requirements and enhancing transferability. We provide the first national-level dataset of 21 million individual fields for Mozambique (covering ~800,000 km2) for 2023. Our maps separate active cropland from non-agricultural land use with an overall accuracy of 93% and balanced omission and commission errors. Field-level spatial agreement reached median intersection over union (IoU) scores of 0.81, advancing the state-of-the-art in large-area field delineation in complex smallholder systems. The active cropland maps capture fragmented rural regions with low cropland shares not yet identified in global land cover or cropland maps. These regions are mostly located in agricultural frontier regions which host 7-9% of the Mozambican population. Field size in Mozambique is very low overall, with half of the fields being smaller than 0.16 ha, and 83% smaller than 0.5 ha. Mean field size at aggregate spatial resolution (0.05{\deg}) is 0.32 ha, but it varies strongly across gradients of accessibility, population density, and net forest cover change. This variation reflects a diverse set of actors, ranging from semi-subsistence smallholder farms to medium-scale commercial farming, and large-scale farming operations. Our results highlight that field size is a key indicator relating to socio-economic and environmental outcomes of agriculture (e.g., food production, livelihoods, deforestation, biodiversity), as well as their trade-offs.
Related papers
- Satellite-based Rabi rice paddy field mapping in India: a case study on Telangana state [0.0]
This study developed a phenology-driven framework that adapts to local agro-ecological variations across 32 districts in India during the 2018-19 rice season.<n>Our district-specific calibration approach achieved 93.3% overall accuracy, an 8.0 percentage point improvement over conventional regional clustering methods.
arXiv Detail & Related papers (2025-07-07T16:47:37Z) - Agri-LLaVA: Knowledge-Infused Large Multimodal Assistant on Agricultural Pests and Diseases [49.782064512495495]
We construct the first multimodal instruction-following dataset in the agricultural domain.<n>This dataset covers over 221 types of pests and diseases with approximately 400,000 data entries.<n>We propose a knowledge-infused training method to develop Agri-LLaVA, an agricultural multimodal conversation system.
arXiv Detail & Related papers (2024-12-03T04:34:23Z) - Local vs. Global: Local Land-Use and Land-Cover Models Deliver Higher Quality Maps [3.606726772030176]
In 2023, 58.0% of the African population experienced moderate to severe food insecurity, with 21.6% facing severe food insecurity.<n>We propose a data-centric framework with a teacher-student model setup, which uses diverse data sources to produce local land-cover maps.<n>Our framework achieved higher quality maps, with improvements of 0.14 in the F1 score and 0.21 in Intersection-over-Union, compared to the best global model.
arXiv Detail & Related papers (2024-12-01T11:48:58Z) - Agricultural Landscape Understanding At Country-Scale [7.978859577060083]
We use high resolution imagery and a UNet style segmentation model to generate the first of its kind national-scale multi-class panoptic segmentation output.
We have been able to identify individual fields across 151.7M hectares, and delineating key features such as water resources and vegetation.
arXiv Detail & Related papers (2024-11-08T06:29:02Z) - The unrealized potential of agroforestry for an emissions-intensive agricultural commodity [48.652015514785546]
We use machine learning to generate estimates of shade-tree cover and carbon stocks across a West African region.
We find that existing shade-tree cover is low, and not spatially aligned with climate threat.
But we also find enormous unrealized potential for the sector to counterbalance a large proportion of their high carbon footprint annually.
arXiv Detail & Related papers (2024-10-28T10:02:32Z) - HarvestNet: A Dataset for Detecting Smallholder Farming Activity Using
Harvest Piles and Remote Sensing [50.4506590177605]
HarvestNet is a dataset for mapping the presence of farms in the Ethiopian regions of Tigray and Amhara during 2020-2023.
We introduce a new approach based on the detection of harvest piles characteristic of many smallholder systems.
We conclude that remote sensing of harvest piles can contribute to more timely and accurate cropland assessments in food insecure regions.
arXiv Detail & Related papers (2023-08-23T11:03:28Z) - Jalisco's multiclass land cover analysis and classification using a
novel lightweight convnet with real-world multispectral and relief data [51.715517570634994]
We present our novel lightweight (only 89k parameters) Convolution Neural Network (ConvNet) to make LC classification and analysis.
In this work, we combine three real-world open data sources to obtain 13 channels.
Our embedded analysis anticipates the limited performance in some classes and gives us the opportunity to group the most similar.
arXiv Detail & Related papers (2022-01-26T14:58:51Z) - Unlocking large-scale crop field delineation in smallholder farming
systems with transfer learning and weak supervision [14.98900824231117]
Crop field boundaries aid in mapping crop types, predicting yields, and delivering field-scale analytics to farmers.
Recent years have seen the successful application of deep learning to delineating field boundaries in industrial agricultural systems.
We demonstrate the methods' success in India where we efficiently generated 10,000 new field labels.
arXiv Detail & Related papers (2022-01-13T03:01:06Z) - Farmland Parcel Delineation Using Spatio-temporal Convolutional Networks [77.63950365605845]
Farm parcel delineation provides cadastral data that is important in developing and managing climate change policies.
This data can also be useful for the agricultural insurance sector for assessing compensations following damages associated with extreme weather events.
Using satellite imaging can be a scalable and cost effective manner to perform the task of farm parcel delineation.
arXiv Detail & Related papers (2020-04-11T19:49:09Z) - Agriculture-Vision: A Large Aerial Image Database for Agricultural
Pattern Analysis [110.30849704592592]
We present Agriculture-Vision: a large-scale aerial farmland image dataset for semantic segmentation of agricultural patterns.
Each image consists of RGB and Near-infrared (NIR) channels with resolution as high as 10 cm per pixel.
We annotate nine types of field anomaly patterns that are most important to farmers.
arXiv Detail & Related papers (2020-01-05T20:19:33Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.