INTEGRATION OF ATTENTION-BASED DEEP LEARNING INTO MODELS OF DRYLAND EXPANSION AND ECOLOGICAL RESILIENCE
DOI:
https://doi.org/10.5281/zenodo.23279975Abstract
Dryland expansion, driven by climate change and unsustainable land use, poses severe risks to ecosystems, agriculture, and global sustainability. Early detection of dryland regions is crucial for timely intervention and ecological preservation. In this study, we propose an enhanced dryland detection framework built upon the Single Shot MultiBox Detector (SSD) baseline, augmented with Attention Gate (AG) mechanisms inspired by Attention U-Net. By embedding AGs into each additional convolutional layer, the model selectively emphasizes environmentally significant spatial features while suppressing irrelevant background responses, thereby improving localization precision and robustness. We curated a high-resolution RGB dataset of diverse dryland-prone regions, incorporating systematic preprocessing and data augmentation strategies to capture heterogeneous degradation patterns. Experimental evaluations demonstrate that the proposed model achieves a mean average precision ([email protected]) of 88.9%, surpassing baseline detectors such as YOLOv5s, RetinaNet, and Faster R-CNN, while maintaining real-time performance at 43.7 FPS. These results highlight the model’s effectiveness in balancing accuracy, efficiency, and generalization, making it a promising tool for large-scale, real-time environmental monitoring and dryland management.Keywords
dryland detection, ecological monitoring, attention gate, environmental degradation, climate change resilienceReferences
Sahoo, C., Saini, A., Vandana Devi, V.S., Saha, A. and Fayezizadeh, M.R., 2025. Revitalizing Dryland Soils: Strategies for Sustainable Management. In Ecologically Mediated Development: Promoting Biodiversity Conservation and Food Security (pp. 399-418). Singapore: Springer Nature Singapore.
Elouafi, Ismahane. “Drylands under pressure: Science and solutions for global stability.” Science 387, no. 6735 (2025): eadv6563.
Timis-Gansac, V., Dinca, L., Constandache, C., Murariu, G., Cheregi, G. and Timofte, C.S.C., 2025. Conservation biodiversity in arid areas: A review. Sustainability, 17(6), p.2422.
Qian, J., Zhao, H., Wang, X., Wang, T., Feng, Z., Cao, C., Li, X. and Zhang, A., 2025. Declining suitability for conversion of drylands to paddy fields in Northeast China: Impact of future climate and socio-economic changes. Geography and Sustainability, 6(1), p.100199.
Ren, Z., Li, C., Fu, B., Zhou, W., Chen, X., Wang, S. and Stringer, L.C., 2025. Detecting Zone‐Type Thresholds for Soil Organic, Inorganic, and Total Carbon Pools in China’s Drylands. Global Change Biology, 31(8), p.e70427.
IPCC. (2019). Climate change and land: An IPCC special report on climate change, desertification, land degradation, sustainable land management, food security, and greenhouse gas fluxes in terrestrial ecosystems. IPCC. https://www. ipcc.ch/srccl/
Su, Y., Xia, H., Feng, Q., Liu, W., Zhang, P., Zhang, J., Zhu, M., Cheng, W. and Yin, X., 2025. Climate-smart protected areas in drylands can effectively safeguard biodiversity without expanding boundaries. Land Use Policy, 158, p.107723.
Zhu, X. X., Tuia, D., Mou, L., Xia, G. S., Zhang, L., Xu, F., & Fraundorfer, F. (2017). Deep learning in remote sensing: A comprehensive review and list of resources. IEEE Geoscience and Remote Sensing Magazine, 5(4), 8–36. https:// doi.org/10.1109/MGRS.2017.2762307
Li, C., Guo, S., Huang, Q., Mu, H., Yuan, B., Xia, Z., Fang, H., Zhang, W., Tang, P. and Du, P., 2025. Dynamic monitoring of fine-grained ecological vulnerability in dryland urban agglomeration integrating novel remote sensing index and explainable machine learning. GIScience & Remote Sensing, 62(1), p.2528302.
Chiloane, C.N., Dube, T., Sibanda, M., Dalu, T. and Shoko, C., 2025. A Summary of Recent Advances in the Literature on Machine Learning Techniques for Remote Sensing of Groundwater Dependent Ecosystems (GDEs) from Space. Remote Sensing, 17(8), p.1460.
Su, T.C., Wu, T.C. and Chen, H.J., 2025. Improving Agricultural Efficiency of Dry Farmlands by Integrating Unmanned Aerial Vehicle Monitoring Data and Deep Learning. Land, 14(6), p.1179.
Li, K., Wan, G., Cheng, G., Meng, L., & Han, J. (2020). Object detection in optical remote sensing images: A survey and a new benchmark. ISPRS Journal of Photogrammetry and Remote Sensing, 159, 296–307. https://doi.org/10.1016/j. isprsjprs.2019.11.023
Lin, T. Y., Goyal, P., Girshick, R., He, K., & Dollár, P. (2017). Focal loss for dense object detection. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) (pp. 2980–2988). https://doi.org/10.1109/ICCV.2017.324
Qi, Z., Wang, J., Yang, G. and Wang, Y., 2025. Lightweight YOLOv8-Based Model for Weed Detection in Dryland Spring Wheat Fields. Sustainability, 17(13), p.6150.
Wang, H., Liu, Q., Gui, D., Liu, Y., Feng, X., Qu, J., Zhao, J. and Wei, G., 2024. Automatedly identify dryland threatened species at large scale by using deep learning. Science of the Total Environment, 917, p.170375.
David, R.M., Rosser, N.J. and Donoghue, D.N., 2022. Remote sensing for monitoring tropical dryland forests: A review of current research, knowledge gaps and future directions for Southern Africa. Environmental Research Communications, 4(4), p.042001.
Dutra, A.C., Srivastava, A., Ganem, K.A., Arai, E., Huete, A. and Shimabukuro, Y.E., 2025. Remote Sensing- Based Phenology of Dryland Vegetation: Contributions and Perspectives in the Southern Hemisphere. Remote Sensing, 17(14), p.2503.
Li, C., Guo, S., Huang, Q., Mu, H., Yuan, B., Xia, Z., Fang, H., Zhang, W., Tang, P. and Du, P., 2025. Dynamic monitoring of fine-grained ecological vulnerability in dryland urban agglomeration integrating novel remote sensing index and explainable machine learning. GIScience & Remote Sensing, 62(1), p.2528302.
Su, T.C., Wu, T.C. and Chen, H.J., 2025. Improving Agricultural Efficiency of Dry Farmlands by Integrating Unmanned Aerial Vehicle Monitoring Data and Deep Learning. Land, 14(6), p.1179.
Shokati, H., Mashal, M., Noroozi, A., Mirzaei, S., Mohammadi-Doqozloo, Z., Nabiollahi, K., Taghizadeh-Mehrjardi, R., Khosravani, P., Adhikari, R., Hu, L. and Scholten, T., 2025. Comparing UAV-Based Hyperspectral and Satellite-Based Multispectral Data for Soil Moisture Estimation Using Machine Learning. Water, 17(11), p.1715.
Woo, S., Park, J., Lee, J. Y., & Kweon, I. S. (2018). CBAM: Convolutional block attention module. In Proceedings of the European Conference on Computer Vision (ECCV) (pp. 3–19). https://doi.org/10.1007/978-3-030-01234-2_1
Lamichhane, M., Mehan, S. and Mankin, K.R., 2025. Surface soil moisture prediction using multimodal remote sensing data fusion and machine learning algorithms in semi-arid agricultural region. Science of Remote Sensing, 12, p.100255.
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., & Berg, A. C. (2016). SSD: Single shot multibox detector. In Computer Vision – ECCV 2016 (pp. 21–37). Springer. https://doi.org/10.1007/978-3-319-46448-0_2
Jiang, D., Liu, J., Zhang, H., Liang, W., Luo, Z., An, W., Li, S., Chen, X., Yuan, X. and Gao, S., 2025. CSCA-YOLOv8: A lightweight network model for evaluating drought resistance in mung bean. Plos one, 20(7), p.e0326328.
Nora, L.E.A., Dias, R.L., De Figueiredo, F.A., Mafra, S.B. and Silva, H.S., 2024, December. Evaluating DETR, RetinaNet, and RTMDet Models for Object Detection in Rural Drone Imagery. In 2024 International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA) (pp. 1326-1331). IEEE.
Cheng, G., & Han, J. (2016). A survey on object detection in optical remote sensing images. ISPRS Journal of 68 9/2026 Photogrammetry and Remote Sensing, 117, 11–28. https://doi.org/10.1016/j.isprsjprs.2016.03.014
Zhu, Z., Zhang, Z., Zuo, L., Pan, T., Zhao, X., Wang, X., Sun, F., Xu, J. and Liu, Z., 2022. Study on the classification and change detection methods of drylands in arid and semi-arid regions. Remote Sensing, 14(5), p.1256.
Oktay, O., Schlemper, J., Le Folgoc, L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N. Y., Kainz, B., Glocker, B., & Rueckert, D. (2018). Attention U-Net: Learning where to look for the pancreas. arXiv. https:// arxiv.org/abs/1804.03999
Hou, S., Sun, S., Yin, T., Zhang, Z. and Yan, M., 2025. AMDCnet: attention-gate-based multi-scale decomposition and collaboration network for long-term time series forecasting. Frontiers in Artificial Intelligence, 8, p.1607232.
Downloads
Published
How to Cite
Issue
Section
