Terra MODIS NDVI 및 LST 자료와 RNN-LSTM을 활용한 토양수분 산정
RNN-LSTM Based Soil Moisture Estimation Using Terra MODIS NDVI and LST
2
조회
0
다운로드
6
인용
0
참고문헌
키워드
초록
This study is to estimate the spatial soil moisture using Terra MODIS (Moderate Resolution Imaging Spectroradiometer) satellite data and machinelearning technique. Using the 3 years (2015∼2017) data of MODIS 16 days composite NDVI (Normalized Difference Vegetation Index) and daily LandSurface Temperature (LST), ground measured precipitation and sunshine hour of KMA (Korea Meteorological Administration), the RDA (RuralDevelopment Administration) 10 cm∼30 cm average TDR (Time Domain Reflectometry) measured soil moisture at 78 locations was tested. For dailyanalysis, the missing values of MODIS LST by clouds were interpolated by conditional merging method using KMA surface temperature observationdata, and the 16 days NDVI was linearly interpolated to 1 day interval. By applying the RNN-LSTM (Recurrent Neural Network-Long Short TermMemory) artificial neural network model, 70% of the total period was trained and the rest 30% period was verified. The results showed that thecoefficient of determination (R2), Root Mean Square Error (RMSE), and Nash-Sutcliffe Efficiency were 0.78, 2.76%, and 0.75 respectively. In average,the clay soil moisture was estimated well comparing with the other soil types of silt, loam, and sand. This is because the clay has the intrinsic physicalproperty for having narrow range of soil moisture variation between field capacity and wilting point.
Abstract
This study is to estimate the spatial soil moisture using Terra MODIS (Moderate Resolution Imaging Spectroradiometer) satellite data and machinelearning technique. Using the 3 years (2015∼2017) data of MODIS 16 days composite NDVI (Normalized Difference Vegetation Index) and daily LandSurface Temperature (LST), ground measured precipitation and sunshine hour of KMA (Korea Meteorological Administration), the RDA (RuralDevelopment Administration) 10 cm∼30 cm average TDR (Time Domain Reflectometry) measured soil moisture at 78 locations was tested. For dailyanalysis, the missing values of MODIS LST by clouds were interpolated by conditional merging method using KMA surface temperature observationdata, and the 16 days NDVI was linearly interpolated to 1 day interval. By applying the RNN-LSTM (Recurrent Neural Network-Long Short TermMemory) artificial neural network model, 70% of the total period was trained and the rest 30% period was verified. The results showed that thecoefficient of determination (R2), Root Mean Square Error (RMSE), and Nash-Sutcliffe Efficiency were 0.78, 2.76%, and 0.75 respectively. In average,the clay soil moisture was estimated well comparing with the other soil types of silt, loam, and sand. This is because the clay has the intrinsic physicalproperty for having narrow range of soil moisture variation between field capacity and wilting point.
참고문헌 (27)
- David Aubert, "Sequential assimilation of soil moisture and streamflow data in a conceptual rainfall–runoff model", Journal of Hydrology, 280(1-4), pp.145~161 (2003), Elsevier BV[DOI]
- Rowan D. Barling, "A quasi-dynamic wetness index for characterizing the spatial distribution of zones of surface saturation and soil water content", Water Resources Research, 30(4), pp.1029~1044 (1994), American Geophysical Union (AGU)[DOI]
- Aiguo Dai, "A Global Dataset of Palmer Drought Severity Index for 1870–2002: Relationship with Soil Moisture and Effects of Surface Warming", Journal of Hydrometeorology, 5(6), pp.1117~1130 (2004), American Meteorological Society[DOI]
- T FARRAR, "The influence of soil type on the relationships between NDVI, rainfall, and soil moisture in semiarid Botswana. II. NDVI response to soil oisture", Remote Sensing of Environment, 50(2), pp.121~133 (1994), Elsevier BV[DOI]
- Gers, F. A., "Learning precise timing with LSTM recurrent networks", Journal of Machine Learning Research, 3, pp.115~143 (2002)
- R. R. Gillies, "A verification of the 'triangle' method for obtaining surface soil water content and energy fluxes from remote measurements of the Normalized Difference Vegetation Index (NDVI) and surface e", International Journal of Remote Sensing, 18(15), pp.3145~3166 (2010), Informa UK Limited[DOI]
- Huete, A. R., "MODIS Vegetation Index (MOD13) Algorithm Theoretical Basis Document Version 3", ~ (1999)
- Hutchinson, J. S., "Continuous soil moisture mapping using MODIS NDVI and LST products", Papers and Proceedings of Applied Geography Conferences, 29, pp.140~ (2006)
- 주재영, "수문기상자료를 이용한 설마천의 토양수분 예측", 대한토목학회 논문집B, 30(5), pp.437~444 (2010), 대한토목학회
- Chunggil Jung, "A Study of Spatial Soil Moisture Estimation Using a Multiple Linear Regression Model and MODIS Land Surface Temperature Data Corrected by Conditional Merging", Remote Sensing, 9(8), pp.870~ (2017), MDPI AG[DOI]
- Kim, B. S., "Flood simulation using the gauge-adjusted radar rainfall and physics-based distributed hydrologic model", Hydrological Processes, 22(22), pp.4400~4414 (2016)[DOI]
- 김대선, "회귀크리깅을 이용한 AMSR2 토양수분자료의 다운스케일링", 한국지도학회지, 17(2), pp.99~110 (2017), 한국지도학회
- 김광섭, "위성관측 토양수분과 지상관측망 자료의 상관성 분석", 한국지리정보학회지, 14(2), pp.69~81 (2011), 한국지리정보학회
- Jongyoun Kim, "Improving Spatial Soil Moisture Representation Through Integration of AMSR-E and MODIS Products", IEEE Transactions on Geoscience and Remote Sensing, 50(2), pp.446~460 (2012), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- 김영호, "딥러닝을 이용한 남한 500미터 해상도의 일단위 토양수분 산출", 한국지도학회지, 17(3), pp.109~121 (2017), 한국지도학회
- 이용관, "다중선형 회귀모형과 천리안 지면온도를 활용한 토양수분 산정 연구", 한국농공학회논문집, 59(1), pp.11~20 (2017), 한국농공학회
- B. Narasimhan, "ESTIMATION OF LONG-TERM SOIL MOISTURE USING A DISTRIBUTED PARAMETER HYDROLOGIC MODEL AND VERIFICATION USING REMOTELY SENSED DATA", Transactions of the ASAE, 48(3), pp.1101~1113 (2005), American Society of Agricultural and Biological Engineers (ASABE)[DOI]
- 박정아, "인공신경망을 이용한 용담댐 유역 공간 토양수분 분포도 산정", 대한지리학회지, 46(3), pp.319~330 (2011), 대한지리학회
- 박선엽, "미중부 대평원지역의 기후학적 수분수지 파악을 위한 MODIS 지표복사온도 자료분석", 국토지리학회지, 37(3), pp.4~ (2003), 국토지리학회
- Yang Qiu, "Spatiotemporal prediction of soil moisture content using multiple-linear regression in a small catchment of the Loess Plateau, China", CATENA, 54(1-2), pp.173~195 (2003), Elsevier BV[DOI]
- 신동하, "RNN과 LSTM을 이용한 주가 예측율 향상을 위한 딥러닝 모델", 한국정보기술학회논문지, 15(10), pp.9~16 (2017), 한국정보기술학회[DOI]
- Su, S. L., "A critical review of soil moisture measurement", Measurement, 54, pp.92~105 (2014)[DOI]
- Wang, L., "Surface soil moisture estimates from AMSR-E observations over an arid area", Hydrology and Earth System Sciences Discussions, 6(1), pp.1055~1087 (2009)
- Wang, Z. M., "MODIS land-surface temperature algorithm theoretical basis document (LST ATBD)", Institute for Computational Earth System Science, ~ (1999)
- Zhengming Wan, "A generalized split-window algorithm for retrieving land-surface temperature from space", IEEE Transactions on Geoscience and Remote Sensing, 34(4), pp.892~905 (1996), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Z. Wan, "Using MODIS Land Surface Temperature and Normalized Difference Vegetation Index products for monitoring drought in the southern Great Plains, USA", International Journal of Remote Sensing, 25(1), pp.61~72 (2010), Informa UK Limited[DOI]
- M ZRIBI, "New methodology for soil surface moisture estimation and its application to ENVISAT-ASAR multi-incidence data inversion", Remote Sensing of Environment, 96(3-4), pp.485~496 (2005), Elsevier BV[DOI]