• Acta Optica Sinica
  • Vol. 38, Issue 10, 1030001 (2018)
Xiangyu Ge1、2、3、*, Jianli Ding1、2、3、*, Jingzhe Wang1、2、3, Fei Wang1、2、3, Lianghong Cai1、2、3, and Huilan Sun4
Author Affiliations
  • 1 College of Resource and Environment Sciences, Xinjiang University, Urumqi, Xinjiang 830046, China
  • 2 Key Laboratory of Oasis Ecology, Xinjiang University, Urumqi, Xinjiang 830046, China
  • 3 Key Laboratory of Smart City and Environment Modelling of Higher Education Institute, Xinjiang University, Urumqi, Xinjiang 830046, China
  • 4 School of Geographical Science and Tourism, Xinjiang Normal University, Urumqi, Xinjiang 830054, China
  • show less
    DOI: 10.3788/AOS201838.1030001 Cite this Article Set citation alerts
    Xiangyu Ge, Jianli Ding, Jingzhe Wang, Fei Wang, Lianghong Cai, Huilan Sun. Estimation of Soil Moisture Content Based on Competitive Adaptive Reweighted Sampling Algorithm Coupled with Machine Learning[J]. Acta Optica Sinica, 2018, 38(10): 1030001 Copy Citation Text show less
    Mean-standard deviation distribution of soil-residual prediction for full-sample MCCV
    Fig. 1. Mean-standard deviation distribution of soil-residual prediction for full-sample MCCV
    Flow chart of calculation process for experience and model
    Fig. 2. Flow chart of calculation process for experience and model
    Spectral reflectance of soils with different SMCs
    Fig. 3. Spectral reflectance of soils with different SMCs
    Variable filtering process using CARS. (a) Variation in wavelength variable number; (b) variation in RMSECV; (c) trend of variable regression coefficient when RMSECV is minimum
    Fig. 4. Variable filtering process using CARS. (a) Variation in wavelength variable number; (b) variation in RMSECV; (c) trend of variable regression coefficient when RMSECV is minimum
    Mean reflectance of soil samples and optimal spectral bands
    Fig. 5. Mean reflectance of soil samples and optimal spectral bands
    Predicted and measured SMCs using ELM model
    Fig. 6. Predicted and measured SMCs using ELM model
    Sample typeNumberMaximumMinimumMeanStandard deviationCoefficient of variation
    Whole set770.2520.0210.14210.0490.3458
    Calibration set620.2520.0210.14060.0510.3659
    Validation set150.2160.0670.14830.0390.2637
    Table 1. Statistical characteristics of SMC of soil samples
    ModelVariable numberCalibration setPrediction set
    RMSER2RMSER2RPDRPIQ
    PLSR200.4840.4780.6220.6170.5220.18401
    BPNN200.0270.7060.0240.7992.0161.90200
    RFR200.0240.8720.0210.8981.6472.18900
    ELM200.0160.8790.0150.9183.1233.32500
    Table 2. Estimated SMC
    ModelRatio of calculation to predictionVariable numberCalibration setPrediction set
    RMSER2RMSER2RPDRPIQ
    BPNN62∶15200.0270.7060.0240.7992.0161.902
    57∶20200.0200.8420.0230.8001.8261.499
    52∶25200.0230.7650.0240.8001.9472.010
    RFR62∶15200.0240.8720.0210.8981.6472.189
    57∶20200.0240.8630.0130.8972.2173.073
    52∶25200.0250.8560.0140.8892.2023.041
    ELM62∶15200.0160.8790.0150.9183.1233.325
    57∶20200.0190.8690.0140.9193.1023.241
    52∶25200.0150.8770.0160.9182.5692.958
    Table 3. Predicted SMC based on different ratios of calibration to prediction
    Xiangyu Ge, Jianli Ding, Jingzhe Wang, Fei Wang, Lianghong Cai, Huilan Sun. Estimation of Soil Moisture Content Based on Competitive Adaptive Reweighted Sampling Algorithm Coupled with Machine Learning[J]. Acta Optica Sinica, 2018, 38(10): 1030001
    Download Citation