Local vs. Global: Local Land-Use and Land-Cover Models Deliver Higher Quality Maps
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916517623365632 |
|---|---|
| author | Tadesse, Girmaw Abebe Robinson, Caleb Mwangi, Charles Maina, Esther Nyakundi, Joshua Marotti, Luana Hacheme, Gilles Quentin Alemohammad, Hamed Dodhia, Rahul Ferres, Juan M. Lavista |
| author_facet | Tadesse, Girmaw Abebe Robinson, Caleb Mwangi, Charles Maina, Esther Nyakundi, Joshua Marotti, Luana Hacheme, Gilles Quentin Alemohammad, Hamed Dodhia, Rahul Ferres, Juan M. Lavista |
| contents | In 2023, 58.0% of the African population experienced moderate to severe food insecurity, with 21.6% facing severe food insecurity. Land-use and land-cover maps provide crucial insights for addressing food insecurity by improving agricultural efforts, including mapping and monitoring crop types and estimating yield. The development of global land-cover maps has been facilitated by the increasing availability of earth observation data and advancements in geospatial machine learning. However, these global maps exhibit lower accuracy and inconsistencies in Africa, partly due to the lack of representative training data. To address this issue, we propose a data-centric framework with a teacher-student model setup, which uses diverse data sources of satellite images and label examples to produce local land-cover maps. Our method trains a high-resolution teacher model on images with a resolution of 0.331 m/pixel and a low-resolution student model on publicly available images with a resolution of 10 m/pixel. The student model also utilizes the teacher model's output as its weak label examples through knowledge transfer. We evaluated our framework using Murang'a county in Kenya, renowned for its agricultural productivity, as a use case. Our local models 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. Our evaluation also revealed inconsistencies in existing global maps, with a maximum agreement rate of 0.30 among themselves. Our work provides valuable guidance to decision-makers for driving informed decisions to enhance food security. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_00777 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Local vs. Global: Local Land-Use and Land-Cover Models Deliver Higher Quality Maps Tadesse, Girmaw Abebe Robinson, Caleb Mwangi, Charles Maina, Esther Nyakundi, Joshua Marotti, Luana Hacheme, Gilles Quentin Alemohammad, Hamed Dodhia, Rahul Ferres, Juan M. Lavista Computer Vision and Pattern Recognition Artificial Intelligence In 2023, 58.0% of the African population experienced moderate to severe food insecurity, with 21.6% facing severe food insecurity. Land-use and land-cover maps provide crucial insights for addressing food insecurity by improving agricultural efforts, including mapping and monitoring crop types and estimating yield. The development of global land-cover maps has been facilitated by the increasing availability of earth observation data and advancements in geospatial machine learning. However, these global maps exhibit lower accuracy and inconsistencies in Africa, partly due to the lack of representative training data. To address this issue, we propose a data-centric framework with a teacher-student model setup, which uses diverse data sources of satellite images and label examples to produce local land-cover maps. Our method trains a high-resolution teacher model on images with a resolution of 0.331 m/pixel and a low-resolution student model on publicly available images with a resolution of 10 m/pixel. The student model also utilizes the teacher model's output as its weak label examples through knowledge transfer. We evaluated our framework using Murang'a county in Kenya, renowned for its agricultural productivity, as a use case. Our local models 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. Our evaluation also revealed inconsistencies in existing global maps, with a maximum agreement rate of 0.30 among themselves. Our work provides valuable guidance to decision-makers for driving informed decisions to enhance food security. |
| title | Local vs. Global: Local Land-Use and Land-Cover Models Deliver Higher Quality Maps |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2412.00777 |