山崩具有強大的破壞力與高度不可預測性，使其成為最嚴重的自然災害之一，嚴重威脅人類的生命與財產安全。台灣位於板塊交界處，且受低緯度熱帶與副熱帶氣候影響，地震頻繁、地形複雜，並伴隨豐沛降雨與颱風侵襲，使台灣成為山崩災害的高風險區域。因此，如何快速且精確地偵測山崩範圍，協助政府進行災害監測與防範，具有重要的實務價值。本研究提出一種結合深度學習語意分割技術的二階段分析框架，用於崩塌地變遷偵測與分類。該框架設計考量三個層面：(1) 資料面：輸入特徵涵蓋光譜、植生、紋理與地形等多元資料，具高度異質性，透過分階段訓練可降低學習難度；(2) 任務面：多類別分類具挑戰性且樣本不均，先進行變遷偵測再分類，有助模型聚焦變異區域；(3) 架構面：所用模型雖專長於像素級分類，卻不具備變遷特徵提取模組，藉由第一階段產製變遷圖，可有效引導後續分類。整體流程整合雙時相影像、單時期地形因子與變遷特徵，並透過逐步訓練提升模型效能。第一階段以未正規化特徵進行二元分類，區分變遷與非變遷區域；第二階段則使用正規化特徵並結合第一階段結果，將變遷區域細分為植生與裸露地、舊崩塌地、新崩塌地與植生恢復區等四類。此逐步訓練策略能有效提升模型的分類效能，特別是在變遷細節辨識上。
本研究以2016 年與 2022 年的荖濃溪流域，以及 2019 年與 2021 年的台灣中部山區進行模型訓練與測試。模型表現以精確度（Precision）、召回率（Recall）、F1 分數（F1-score）和整體準確度（Overall Accuracy）進行評估。研究結果顯示，二階段分析策略能有效提升分類精度，具體而言，模型在兩個研究區的舊崩塌地類別中 F1-score 超過 0.9，在新崩塌地類別中超過 0.7，在植生恢復類別中超過 0.7 並達到 0.8。這些結果證明所提出的框架在崩塌地變遷偵測與分類中具備良好效能，對未來災害監測與管理應用具有潛在的幫助。

Landslides possess immense destructive power and high unpredictability, making them one of the most threatening natural disasters causing significant threats to human lives and property. Taiwan is located at the junction of tectonic plates and is influenced by a tropical and subtropical climate due to its low-latitude location, leading to frequent earthquakes, complex terrain, and extreme weather. These factors make Taiwan highly vulnerable to landslide disasters. Therefore, rapidly and accurately detecting landslide occurrences is crucial for disaster monitoring and management. This study proposes a two-step analysis framework that integrates deep learning with semantic segmentation techniques for landslide change detection and classification. The framework is designed based on three key considerations: (1) Data perspective: the input features consist of diverse and heterogeneous data sources, including spectral, vegetation, textural, and topographic factors. A stepwise training strategy is adopted to reduce learning difficulty; (2) Task perspective: multi-class classification of landslide changes is challenging due to sample imbalance. Performing change detection before classification helps the model focus on areas of interest; (3) Structural perspective: although the adopted model specializes in pixel-wise classification, it lacks a dedicated module for extracting change features. Thus, a preliminary change map generated in the first step effectively guides the subsequent classification. The overall process integrates bi-temporal imagery, single-period topographic factors, and derived change features, with progressive training to improve model performance. The two-step strategy begins with the model learning raw, unnormalized features to perform binary classification, distinguishing changed and unchanged regions. In the second step, the model utilizes normalized features combined with predictions from the first step, further refining the classification into four categories: vegetation and bare land, old landslide, new landslide, and vegetation reclaimed. This progressive training strategy effectively improves classification performance, particularly in detecting subtle change details.
Two study areas were selected for model training and testing including the Laonong River Basin (2016 and 2022) and the Central Taiwan Mountain Region (2019 and 2021). Model performance is assessed using Precision, Recall, F1-score, and Overall Accuracy as evaluation metrics. Results of this analyze demonstrate that the two-step analysis strategy effectively improves classification accuracy. Specifically, the model achieved more than 0.9 F1-scores for old landslide in both study areas, over 0.7 for new landslide, and exceeding 0.7 and reaching 0.8 for vegetation reclaimed. The effectiveness of the proposed framework in landslide change detection and classification has a great potential for improving future disaster monitoring and management.

Ballabio, C., & Sterlacchini, S. (2012). Support vector machines for landslide susceptibility mapping: the Staffora River Basin case study, Italy. Mathematical geosciences, 44, 47-70.
Bao, S., Liu, J., Wang, L., & Zhao, X. (2022). Application of transformer models to landslide susceptibility mapping. Sensors, 22(23), 9104.
Behling, R., Roessner, S., Kaufmann, H., & Kleinschmit, B. (2014). Automated Spatiotemporal Landslide Mapping over Large Areas Using RapidEye Time Series Data. Remote Sensing, 6(9), 8026-8055. https://doi.org/10.3390/rs6098026
Bid, S. (2016). Change detection of vegetation cover by NDVI technique on catchment area of the Panchet Hill Dam, India. International Journal of Research in Geography (IJRG), 2(3), 11-20.
Bragagnolo, L., Rezende, L. R., da Silva, R. V., & Grzybowski, J. M. V. (2021). Convolutional neural networks applied to semantic segmentation of landslide scars. Catena, 201. https://doi.org/10.1016/j.catena.2021.105189
Breiman, L. (2001). Random forests. Machine learning, 45, 5-32.
Buda, M., Maki, A., & Mazurowski, M. A. (2018). A systematic study of the class imbalance problem in convolutional neural networks. Neural networks, 106, 249-259.
Chen, J., Lu, Y., Yu, Q., Luo, X., Adeli, E., Wang, Y., Lu, L., Yuille, A. L., & Zhou, Y. (2021). TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation. arXiv:2102.04306. Retrieved February 01, 2021, from https://ui.adsabs.harvard.edu/abs/2021arXiv210204306C
Chen, W., Li, X., Wang, Y., Chen, G., & Liu, S. (2014). Forested landslide detection using LiDAR data and the random forest algorithm: A case study of the Three Gorges, China. Remote Sensing of Environment, 152, 291-301.
Chibuike, O., & Yang, X. (2024). Convolutional Neural Network–Vision Transformer Architecture with Gated Control Mechanism and Multi-Scale Fusion for Enhanced Pulmonary Disease Classification. Diagnostics, 14(24), 2790.
Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine learning, 20, 273-297.
Cui, Y., Jia, M., Lin, T.-Y., Song, Y., & Belongie, S. (2019). Class-balanced loss based on effective number of samples. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition,
Ding, A., Zhang, Q., Zhou, X., & Dai, B. (2016). Automatic recognition of landslide based on CNN and texture change detection. 2016 31st Youth Academic Annual Conference of Chinese Association of Automation (YAC),
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., & Gelly, S. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929.
Fan, X., Juang, C. H., Wasowski, J., Huang, R., Xu, Q., Scaringi, G., van Westen, C. J., & Havenith, H.-B. (2018). What we have learned from the 2008 Wenchuan Earthquake and its aftermath: A decade of research and challenges. Engineering Geology, 241, 25-32. https://doi.org/10.1016/j.enggeo.2018.05.004
Ghorbanzadeh, O., Blaschke, T., Gholamnia, K., Meena, S. R., Tiede, D., & Aryal, J. (2019). Evaluation of Different Machine Learning Methods and Deep-Learning Convolutional Neural Networks for Landslide Detection. Remote Sensing, 11(2). https://doi.org/10.3390/rs11020196
Ghorbanzadeh, O., Xu, Y., Ghamisi, P., Kopp, M., & Kreil, D. (2022). Landslide4sense: Reference benchmark data and deep learning models for landslide detection. arXiv preprint arXiv:2206.00515.
Glenn, N. F., Streutker, D. R., Chadwick, D. J., Thackray, G. D., & Dorsch, S. J. (2006). Analysis of LiDAR-derived topographic information for characterizing and differentiating landslide morphology and activity. Geomorphology, 73(1-2), 131-148.
Goodfellow, I., Bengio, Y., Courville, A., & Bengio, Y. (2016). Deep learning (Vol. 1). MIT press Cambridge.
Guo, Z., Zhang, L., & Zhang, D. (2010). A completed modeling of local binary pattern operator for texture classification. IEEE transactions on image processing, 19(6), 1657-1663.
Guzzetti, F., Mondini, A. C., Cardinali, M., Fiorucci, F., Santangelo, M., & Chang, K.-T. (2012). Landslide inventory maps: New tools for an old problem. Earth-Science Reviews, 112(1-2), 42-66. https://doi.org/10.1016/j.earscirev.2012.02.001
He, K., Zhang, X., Ren, S., & Sun, J. (2016a). Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition,
He, K., Zhang, X., Ren, S., & Sun, J. (2016b). Identity mappings in deep residual networks. Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part IV 14,
Highland, L. M., & Bobrowsky, P. (2008). The landslide handbook-A guide to understanding landslides. US Geological Survey.
Ji, S., Yu, D., Shen, C., Li, W., & Xu, Q. (2020a). Landslide detection from an open satellite imagery and digital elevation model dataset using attention boosted convolutional neural networks. Landslides, 17(6), 1337-1352. https://doi.org/10.1007/s10346-020-01353-2
Ji, S., Yu, D., Shen, C., Li, W., & Xu, Q. (2020b). Landslide detection from an open satellite imagery and digital elevation model dataset using attention boosted convolutional neural networks. Landslides, 17, 1337-1352.
Johnson, J. M., & Khoshgoftaar, T. M. (2019). Survey on deep learning with class imbalance. Journal of big data, 6(1), 1-54.
Kaushal, A., & Sehgal, V. K. (2023). Landslide susceptibility detection using ResNet. 2023 3rd Asian Conference on Innovation in Technology (ASIANCON),
Kinoshita, Y., & Kiya, H. (2019). Convolutional neural networks considering local and global features for image enhancement. 2019 IEEE International Conference on Image Processing (ICIP),
Lacroix, P., Bièvre, G., Pathier, E., Kniess, U., & Jongmans, D. (2018). Use of Sentinel-2 images for the detection of precursory motions before landslide failures. Remote Sensing of Environment, 215, 507-516. https://doi.org/10.1016/j.rse.2018.03.042
Lai, J.-S. (2018). 整合空間資料與資料探勘演算法精進廣域崩塌潛勢評估 National Central University].
LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278-2324.
Lee, S., Hong, S.-M., & Jung, H.-S. (2017). A support vector machine for landslide susceptibility mapping in Gangwon Province, Korea. Sustainability, 9(1), 48.
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollár, P. (2017). Focal loss for dense object detection. Proceedings of the IEEE international conference on computer vision,
Malamud, B. D., Turcotte, D. L., Guzzetti, F., & Reichenbach, P. (2004). Landslide inventories and their statistical properties. Earth Surface Processes and Landforms, 29(6), 687-711. https://doi.org/10.1002/esp.1064
Marjanovic, M., Bajat, B., & Kovacevic, M. (2009). Landslide susceptibility assessment with machine learning algorithms. 2009 International Conference on Intelligent Networking and Collaborative Systems,
Martha, T. R., Kerle, N., Jetten, V., van Westen, C. J., & Kumar, K. V. (2010). Characterising spectral, spatial and morphometric properties of landslides for semi-automatic detection using object-oriented methods. Geomorphology, 116(1-2), 24-36. https://doi.org/10.1016/j.geomorph.2009.10.004
Meena, S. R., Nava, L., Bhuyan, K., Puliero, S., Soares, L. P., Dias, H. C., Floris, M., & Catani, F. (2023). HR-GLDD: a globally distributed dataset using generalized deep learning (DL) for rapid landslide mapping on high-resolution (HR) satellite imagery. Earth Syst. Sci. Data, 15(7), 3283-3298. https://doi.org/10.5194/essd-15-3283-2023
Milletari, F., Navab, N., & Ahmadi, S.-A. (2016). V-net: Fully convolutional neural networks for volumetric medical image segmentation. 2016 fourth international conference on 3D vision (3DV),
Mondini, A. C., Santangelo, M., Rocchetti, M., Rossetto, E., Manconi, A., & Monserrat, O. (2019). Sentinel-1 SAR Amplitude Imagery for Rapid Landslide Detection. Remote Sensing, 11(7). https://doi.org/10.3390/rs11070760
Nichol, J., & Wong, M. S. (2005). Satellite remote sensing for detailed landslide inventories using change detection and image fusion. International journal of remote sensing, 26(9), 1913-1926.
Ojala, T., Pietikäinen, M., & Harwood, D. (1996). A comparative study of texture measures with classification based on featured distributions. Pattern recognition, 29(1), 51-59.
Peng, Z., Huang, W., Gu, S., Xie, L., Wang, Y., Jiao, J., & Ye, Q. (2021). Conformer: Local features coupling global representations for visual recognition. Proceedings of the IEEE/CVF international conference on computer vision,
Rahim, A. A. (2024). Spectral Fidelity and Spatial Enhancement: An Assessment and Cascading of Pan-Sharpening Techniques for Satellite Imagery. arXiv preprint arXiv:2405.18900.
Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18,
San, B. T. (2014). An evaluation of SVM using polygon-based random sampling in landslide susceptibility mapping: The Candir catchment area (western Antalya, Turkey). International Journal of Applied Earth Observation and Geoinformation, 26, 399-412.
Santangelo, M., Cardinali, M., Rossi, M., Mondini, A. C., & Guzzetti, F. (2010). Remote landslide mapping using a laser rangefinder binocular and GPS. Natural Hazards and Earth System Sciences, 10(12), 2539-2546. https://doi.org/10.5194/nhess-10-2539-2010
Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of big data, 6(1), 1-48.
Soeters, R., & van Westen, C. J. (1996). Slope instability recognition, analysis, and zonation. In Landslides, investigation and mitigation (pp. 129-177). National Academy Press.
Story, M., & Congalton, R. G. (1986). Accuracy assessment: a user’s perspective. Photogrammetric Engineering and remote sensing, 52(3), 397-399.
Stumpf, A., & Kerle, N. (2011). Object-oriented mapping of landslides using Random Forests. Remote Sensing of Environment, 115(10), 2564-2577.
Sun, D., Wen, H., Wang, D., & Xu, J. (2020). A random forest model of landslide susceptibility mapping based on hyperparameter optimization using Bayes algorithm. Geomorphology, 362, 107201.
Taalab, K., Cheng, T., & Zhang, Y. (2018). Mapping landslide susceptibility and types using Random Forest. Big Earth Data, 2(2), 159-178.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30.
Warmerdam, F., Rouault, E., & Team, G. D. (2025). gdal_pansharpen – GDAL documentation. https://gdal.org/en/stable/programs/gdal_pansharpen.html
Yang, Z., Xu, C., & Li, L. (2022). Landslide Detection Based on ResU-Net with Transformer and CBAM Embedded: Two Examples with Geologically Different Environments. Remote Sensing, 14(12). https://doi.org/10.3390/rs14122885
Yao, W., Bai, J., Liao, W., Chen, Y., Liu, M., & Xie, Y. (2023). From CNN to Transformer: A Review of Medical Image Segmentation Models. arXiv:2308.05305. Retrieved August 01, 2023, from https://ui.adsabs.harvard.edu/abs/2023arXiv230805305Y
Yun, S., Han, D., Oh, S. J., Chun, S., Choe, J., & Yoo, Y. (2019). Cutmix: Regularization strategy to train strong classifiers with localizable features. Proceedings of the IEEE/CVF international conference on computer vision,