土壤含水量是影響大氣和地球表面水分交換的關鍵指標，直接控制著地球生態環境氣候變化和水循環，為研究地表資源的重要參數。山區的土壤含水量監測可應用於邊坡水土保持、崩塌地監測、森林火災預警等方面。一般土壤含水量的量測大多受到量測儀器時間及空間上的限制，需依靠大量的人力物力才能取得大範圍及長時間的監測資訊，而使用衛星遙測技術進行土壤含水量的推估，可較易取得大範圍且長時間的監測資訊。目前以衛星影像推估大範圍土壤含水量分佈的方法大多著重在農地及低矮植被區域，受限於山區複雜的地形及植被因素，則較少有相關研究應用於山區土壤含水量之監測。本研究試透過機器學習探討遙測影像於山區推估土壤含水量分布狀況，本研究選用歐洲太空總署ESA的Sentinel-1&2系列之開放衛星資料、美國太空總署NASA的MODIS衛星影像以及研究區域的數值高程模型(Digital Elevation Model, DEM)等遙測影像資料。Sentitnel-1為合成孔徑雷達，其影像資訊為後向散射係數，而後向散射係散與土壤含水量有直接的關係；Sentinel-2及MODIS為多光譜衛星，可獲取研究區域的植被及地表資訊；透過DEM來取得山區間的坡度、坡向及地表粗糙度等參數。本研究結合以上遙測影像參數，搭配台灣水土保持局土石流觀測系統中的土壤含水量測站資料，進行機器學習中的隨機森林回歸模型建置。本研究以2020年全年各衛星及測站資料進行運算，推估結果與現地量測值的平均誤差為6.61%，並將模型套用到測站附近區域，觀察該區土壤含水量的分布狀況，根據推估結果進行討論。

Soil moisture monitoring in the mountain area could be applied to ground water conservation, landslide monitoring and forest fire warning. Generally, the measurement of soil moisture is limited by the setup time and space of the measuring instruments. Using satellite image data to estimate the soil moisture could easily to obtain a large-scale and also long-term monitoring information. At present, most method of the soil moisture estimating are focus on agricultural and bare land area. There are few relevant studies focus on mountain area for its complex terrain and vegetation coverage. This study attempts to estimate the soil moisture distribution of mountain area via machine learning method in Taiwan. The raw information are extracted from the satellite data of the Sentinel-1&2 series of the ESA, the MODIS satellite image of NASA and the digital elevation model (DEM) within the research area. This study combines those remote sensing data with soil moisture surveying station data of Taiwan Soil and Water Conservation Bureau to perform a random forest regression. We collected data within the testing site of 2020, and the average absolute error between the estimated result and the in-situ measurement value is 6.61% by self-validation method. The models are also applied to the areas adjacent to station for observing the soil moisture distribution in the area and discuss the relationship to the occurrence of landslide based upon the estimated soil moisture from this work.

Ahmad, S., Kalra, A., & Stephen, H. (2010). Estimating soil moisture using remote sensing data: A machine learning approach. Advances in Water Resources, 33(1), 69-80. doi:10.1016/j.advwatres.2009.10.008
Attema, E. P. W., & Ulaby, F. T. (1978). Vegetation modeled as a water cloud. Radio Science, 13(2), 357-364. doi:10.1029/RS013i002p00357
Baghdadi, N., Zribi, M., Paloscia, S., Verhoest, N., Lievens, H., Baup, F., & Mattia, F. (2015). Semi-Empirical Calibration of the Integral Equation Model for Co-Polarized L-Band Backscattering. Remote Sensing, 7(10), 13626-13640. doi:10.3390/rs71013626
Barrett, B., Dwyer, E., & Whelan, P. (2009). Soil Moisture Retrieval from Active Spaceborne Microwave Observations: An Evaluation of Current Techniques. Remote Sensing, 1(3), 210-242. doi:10.3390/rs1030210
Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5-32. doi:10.1023/a:1010933404324
Chen, K. S., Tzong-Dar, W., Leung, T., Qin, L., Jiancheng, S., & Fung, A. K. (2003). Emission of rough surfaces calculated by the integral equation method with comparison to three-dimensional moment method simulations. IEEE Transactions on Geoscience and Remote Sensing, 41(1), 90-101. doi:10.1109/tgrs.2002.807587
Dubois, P. C., van Zyl, J., & Engman, T. (1995). Measuring soil moisture with imaging radars. IEEE Transactions on Geoscience and Remote Sensing, 33(4), 915-926. doi:10.1109/36.406677
Ezzahar, J., Ouaadi, N., Zribi, M., Elfarkh, J., Aouade, G., Khabba, S., . . . Jarlan, L. (2019). Evaluation of Backscattering Models and Support Vector Machine for the Retrieval of Bare Soil Moisture from Sentinel-1 Data. Remote Sensing, 12(1). doi:10.3390/rs12010072
Filipponi, F. (2019). Sentinel-1 GRD Preprocessing Workflow. Proceedings, 18(1). doi:10.3390/ecrs-3-06201
Freeman, A., & Durden, S. L. (1998). A three-component scattering model for polarimetric SAR data. IEEE Transactions on Geoscience and Remote Sensing, 36(3), 963-973. doi:10.1109/36.673687
Fung, A. K. (1994). Microwave scattering and emission models and their applications. Norwood, MA: Artech House, 1994.
Gao, Q., Zribi, M., Escorihuela, M., Baghdadi, N., & Segui, P. (2018). Irrigation Mapping Using Sentinel-1 Time Series at Field Scale. Remote Sensing, 10(9). doi:10.3390/rs10091495
Gorrab, A., Zribi, M., Baghdadi, N., Lili-Chabaane, Z., & Mougenot, B. (2014, 17-19 March 2014). Multi-frequency analysis of soil moisture vertical heterogeneity effect on radar backscatter. Paper presented at the 2014 1st International Conference on Advanced Technologies for Signal and Image Processing (ATSIP).
Holtgrave, A.-K., Förster, M., Greifeneder, F., Notarnicola, C., & Kleinschmit, B. (2018). Estimation of Soil Moisture in Vegetation-Covered Floodplains with Sentinel-1 SAR Data Using Support Vector Regression. PFG – Journal of Photogrammetry, Remote Sensing and Geoinformation Science, 86(2), 85-101. doi:10.1007/s41064-018-0045-4
Jia, Y., Jin, S., Savi, P., Yan, Q., & Li, W. (2020). Modeling and Theoretical Analysis of GNSS-R Soil Moisture Retrieval Based on the Random Forest and Support Vector Machine Learning Approach. Remote Sensing, 12(22). doi:10.3390/rs12223679
Khabazan, S., Motagh, M., & Hosseini, M. (2013). Evaluation of Radar Backscattering Models IEM, OH, and Dubois using L and C-Bands SAR Data over different vegetation canopy covers and soil depths. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci, 1, W3.
Kornelsen, K. C., & Coulibaly, P. (2013). Advances in soil moisture retrieval from synthetic aperture radar and hydrological applications. Journal of Hydrology, 476, 460-489. doi:10.1016/j.jhydrol.2012.10.044
Kuter, S. (2021). Completing the machine learning saga in fractional snow cover estimation from MODIS Terra reflectance data: Random forests versus support vector regression. Remote Sensing of Environment, 255. doi:10.1016/j.rse.2021.112294
Lee, J.-S. (1981). Speckle analysis and smoothing of synthetic aperture radar images. Computer Graphics and Image Processing, 17(1), 24-32. doi:10.1016/s0146-664x(81)80005-6
Lillesand, T., Kiefer, R. W., & Chipman, J. (2015). Remote sensing and image interpretation: John Wiley & Sons.
Liu, H., Zhao, Z., & Jezek, K. C. (2004). Correction of positional errors and geometric distortions in topographic maps and DEMs using a rigorous SAR simulation technique. Photogrammetric Engineering & Remote Sensing, 70(9), 1031-1042.
Massonnet, D., & Feigl, K. L. (1998). Radar interferometry and its application to changes in the Earth's surface. Reviews of Geophysics, 36(4), 441-500. doi:10.1029/97rg03139
Moran, M. S., McElroy, S., & Watts, J. M. (2006). Radar remote sensing for estimation of surface soil moisture at the watershed scale.
Moran, M. S., Peters-Lidard, C. D., Watts, J. M., & McElroy, S. (2004). Estimating soil moisture at the watershed scale with satellite-based radar and land surface models. Canadian Journal of Remote Sensing, 30(5), 805-826. doi:10.5589/m04-043
Muller, E., & Décamps, H. (2001). Modeling soil moisture–reflectance. Remote Sensing of Environment, 76(2), 173-180. doi:10.1016/s0034-4257(00)00198-x
Nabilah, S. (2020). 使用類神經網路以光學衛星影像推估稻米產量. 成功大學測量及空間資訊學系學位論文, 1-63.
Njoku, E. G., & Entekhabi, D. (1996). Passive microwave remote sensing of soil moisture. Journal of Hydrology, 184(1-2), 101-129. doi:10.1016/0022-1694(95)02970-2
Oh, Y. (2004). Quantitative Retrieval of Soil Moisture Content and Surface Roughness From Multipolarized Radar Observations of Bare Soil Surfaces. IEEE Transactions on Geoscience and Remote Sensing, 42(3), 596-601. doi:10.1109/tgrs.2003.821065
Oh, Y., Sarabandi, K., & Ulaby, F. T. (1992). An empirical model and an inversion technique for radar scattering from bare soil surfaces. IEEE Transactions on Geoscience and Remote Sensing, 30(2), 370-381. doi:10.1109/36.134086
Paloscia, S., Pettinato, S., Santi, E., Notarnicola, C., Pasolli, L., & Reppucci, A. (2013). Soil moisture mapping using Sentinel-1 images: Algorithm and preliminary validation. Remote Sensing of Environment, 134, 234-248. doi:10.1016/j.rse.2013.02.027
Petropoulos, G. P., Ireland, G., & Barrett, B. (2015). Surface soil moisture retrievals from remote sensing: Current status, products & future trends. Physics and Chemistry of the Earth, Parts A/B/C, 83-84, 36-56. doi:10.1016/j.pce.2015.02.009
Puri, S., Stephen, H., & Ahmad, S. (2011). Relating TRMM precipitation radar land surface backscatter response to soil moisture in the Southern United States. Journal of Hydrology, 402(1-2), 115-125. doi:10.1016/j.jhydrol.2011.03.012
Rosenqvist, A., & Killough, B. (2018). A Layman's Interpretation Guide to L-band and C-band Synthetic Aperture Radar data, v2.0.
Schmitt, M. (2014). Reconstruction of urban surface models from multi-aspect and multi-baseline interferometric SAR.
Sharma, P. K., Kumar, D., Srivastava, H. S., & Patel, P. (2018). Assessment of different methods for soil moisture estimation: a review. J. Remote Sens. GIS, 9(1), 57-73.
Shoshany, M., Svoray, T., Curran, P. J., Foody, G. M., & Perevolotsky, A. (2010). The relationship between ERS-2 SAR backscatter and soil moisture: Generalization from a humid to semi-arid transect. International Journal of Remote Sensing, 21(11), 2337-2343. doi:10.1080/01431160050029620
Thoma, D., Moran, M., Bryant, R., Collins, C. H., Rahman, M., & Skirvin, S. (2004, 20-24 Sept. 2004). Comparison of two methods for extracting surface soil moisture from C-band radar imagery. Paper presented at the IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.
Thoma, D. P., Moran, M. S., Bryant, R., Rahman, M., Holifield-Collins, C. D., Skirvin, S., . . . Slocum, K. (2006). Comparison of four models to determine surface soil moisture from C-band radar imagery in a sparsely vegetated semiarid landscape. Water Resources Research, 42(1). doi:10.1029/2004wr003905
Ulaby, F. T., Dubois, P. C., & van Zyl, J. (1996). Radar mapping of surface soil moisture. Journal of Hydrology, 184(1-2), 57-84. doi:10.1016/0022-1694(95)02968-0
Villasensor, J. D., Fatland, D. R., & Hinzman, L. D. (1993). Change detection on Alaska's North Slope using repeat-pass ERS-1 SAR images. IEEE Transactions on Geoscience and Remote Sensing, 31(1), 227-236. doi:10.1109/36.210462
Weidong, L., Baret, F., Xingfa, G., Qingxi, T., Lanfen, Z., & Bing, Z. (2002). Relating soil surface moisture to reflectance. Remote Sensing of Environment, 81(2-3), 238-246. doi:10.1016/s0034-4257(01)00347-9
Zribi, M., Baghdadi, N., Holah, N., & Fafin, O. (2005). New methodology for soil surface moisture estimation and its application to ENVISAT-ASAR multi-incidence data inversion. Remote Sensing of Environment, 96(3-4), 485-496. doi:10.1016/j.rse.2005.04.005
江昭輝, 簡光佑, 莊秉潔, 黨美齡, 李育棋, 洪景山, . . . 蔡徵霖. (2015). 台灣區域土壤含水率觀測網之建置與資料分析. 大氣科學, 43(2), 133-150.
吳怡瑩, 劉哲欣, & 張志新. (2013). 降雨量與表層土壤含水率關係之研究. 社團法人中華水土保持學會 102 年度年會.
肖晶晶. (2020). 利用衛星影像反演臺灣阿里山森林地表土壤含水量. 成功大學地球科學系學位論文, 1-86.
林宜徵. (2011). 應用 MODIS 衛星資料推估地表土壤含水量. 中央大學土木工程學系學位論文, 1-99.
張子瑩, & 林李耀. (2013). 應用 MODIS 影像反演土壤含水率-以泰國 MaeSa 集水區為例. 航測及遙測學刊, 17(1), 67-75.
陳郁琪. (2019). PS-InSAR 技術於台灣山區地形變化偵測誤差因素分析. 成功大學資源工程學系學位論文.
陳錦麟. (2018). 利用 Sentinel-1 & 2 遙測影像推估土壤含水量空間分佈-以桃園石門灌區為例. 臺灣大學生物環境系統工程學研究所學位論文, 1-57.
彭文飛. (2020). 以SMAP衛星遙測配合SAR雷達回波評估土壤含水量分布與崩塌關聯分析. 國立成功大學衛星資訊研究中心.