Random Forests with Bagging and Genetic Algorithms Coupled with Least Trimmed Squares Regression for Soil Moisture Deficit Using SMOS Satellite Soil Moisture

Soil Moisture Deficit (SMD) is a key indicator of soil water content changes and is valuable to a variety of applications, such as weather and climate, natural disasters, agricultural water management, etc. Soil Moisture and Ocean Salinity (SMOS) is a dedicated mission focused on soil moisture retrieval and can be utilized for SMD estimation. In this study, the use of soil moisture derived from SMOS has been provided for the estimation of SMD at a catchment scale. Several approaches for the estimation of SMD are implemented herein, using algorithms such as Random Forests (RF) and Genetic Algorithms coupled with Least Trimmed Squares (GALTS) regression. The results show that for SMD estimation, the RF algorithm performed best as compared to the GALTS, with Root Mean Square Errors (RMSEs) of 0.021 and 0.024, respectively. All in all, our study findings can provide important assistance towards developing the accuracy and applicability of remote sensing-based products for operational use.

[1]  V. Isham,et al.  Design of the HYREX raingauge network , 2000 .

[2]  I. S. Selirio,et al.  Soil moisture-based simulation of forage yield , 1979 .

[3]  Dawei Han,et al.  Assessment of SMOS soil moisture retrieval parameters using tau-omega algorithms for soil moisture deficit estimation , 2014 .

[4]  M. Hakan Satman,et al.  A Genetic Algorithm Based Modification on the LTS Algorithm for Large Data Sets , 2012, Commun. Stat. Simul. Comput..

[5]  Dawei Han,et al.  Sensitivity and uncertainty analysis of mesoscale model downscaled hydro‐meteorological variables for discharge prediction , 2014 .

[6]  Dawei Han,et al.  Performance evaluation of WRF-Noah Land surface model estimated soil moisture for hydrological application: Synergistic evaluation using SMOS retrieved soil moisture , 2015 .

[7]  H. G. Halcrow.  Actuarial Structures for Crop Insurance , 1949 .

[8]  Mario Chica-Olmo,et al.  An assessment of the effectiveness of a random forest classifier for land-cover classification , 2012 .

[9]  Tanvir Islam,et al.  Tree-based genetic programming approach to infer microphysical parameters of the DSDs from the polarization diversity measurements , 2012, Comput. Geosci..

[10]  M. S. Moran,et al.  Estimating crop water deficit using the relation between surface-air temperature and spectral vegetation index , 1994 .

[11]  R. Srinivasan,et al.  Development and evaluation of Soil Moisture Deficit Index (SMDI) and Evapotranspiration Deficit Index (ETDI) for agricultural drought monitoring , 2005 .

[12]  Richard Harding,et al.  An objective assessment of soil-moisture deficit models , 1983 .

[13]  John R. Koza,et al.  Genetic Programming II , 1992 .

[14]  George P. Petropoulos,et al.  Surface soil moisture retrievals from remote sensing: Current status, products & future trends , 2015 .

[15]  Tanvir Islam,et al.  Non-parametric rain/no rain screening method for satellite-borne passive microwave radiometers at 19–85 GHz channels with the Random Forests algorithm , 2014 .

[16]  Justin Sheffield,et al.  A stochastic space-time rainfall forecasting system for real time flow forecasting II: Application of SHETRAN and ARNO rainfall runoff models to the Brue catchment , 2000 .

[17]  George P. Petropoulos,et al.  GIS and Remote Sensing Aided Information for Soil Moisture Estimation: A Comparative Study of Interpolation Techniques , 2019, Resources.

[18]  Vijay Pratap Yadav,et al.  Estimation of winter wheat crop growth parameters using time series Sentinel-1A SAR data , 2018 .

[19]  PETER J. ROUSSEEUW,et al.  Computing LTS Regression for Large Data Sets , 2005, Data Mining and Knowledge Discovery.

[20]  V. Bell,et al.  The sensitivity of catchment runoff models to rainfall data at different spatial scales , 2000 .

[21]  V. Burkett,et al.  Gender and occupational perspectives on adaptation to climate extremes in the Afram Plains of Ghana , 2011, Climatic Change.

[22]  George P. Petropoulos,et al.  Evaporative Fluxes and Surface Soil Moisture Retrievals in a Mediterranean Setting from Sentinel-3 and the "Simplified Triangle" , 2020, Remote. Sens..

[23]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[24]  George P. Petropoulos,et al.  Geoinformation Technologies in Support of Environmental Hazards Monitoring under Climate Change: An Extensive Review , 2021, ISPRS Int. J. Geo Inf..

[25]  George P. Petropoulos,et al.  Coupling remote sensing with a water balance model for soybean yield predictions over large areas , 2019, Earth Science Informatics.

[26]  Robert P. Sheridan,et al.  Random Forest: A Classification and Regression Tool for Compound Classification and QSAR Modeling , 2003, J. Chem. Inf. Comput. Sci..

[27]  R. Moore.  The PDM rainfall-runoff model , 2007 .

[28]  Dawei Han,et al.  Machine Learning Techniques for Downscaling SMOS Satellite Soil Moisture Using MODIS Land Surface Temperature for Hydrological Application , 2013, Water Resources Management.

[29]  Sterling A. Taylor,et al.  USE OF MEAN SOIL MOISTURE TENSION TO EVALUATE THE EFFECT OF SOIL MOISTURE ON CROP YIELDS , 1952 .

[30]  Pieter Cabus,et al.  River flow prediction through rainfall–runoff modelling with a probability-distributed model (PDM) in Flanders, Belgium , 2008 .

[31]  Aradhana Yaduvanshi,et al.  Soil erosion in future scenario using CMIP5 models and earth observation datasets , 2020, Journal of Hydrology.

[32]  Johannes R. Sveinsson,et al.  Random Forests for land cover classification , 2006, Pattern Recognit. Lett..

[33]  Dawei Han,et al.  Indices for calibration data selection of the rainfall‐runoff model , 2010 .

[34]  Marco Borga,et al.  Accuracy of radar rainfall estimates for streamflow simulation , 2002 .

[35]  S. Pinori,et al.  Preparing the ESA-SMOS (Soil Moisture and Ocean Salinity) mission - Overview of the user data products and data distribution strategy , 2008, 2008 Microwave Radiometry and Remote Sensing of the Environment.

[36]  Z. Kundzewicz,et al.  Model-based reconstruction and projections of soil moisture anomalies and crop losses in Poland , 2020, Theoretical and Applied Climatology.

[37]  George P. Petropoulos,et al.  An Operational In Situ Soil Moisture & Soil Temperature Monitoring Network for West Wales, UK: The WSMN Network , 2017, Sensors.

[38]  K. Rushton,et al.  Improved soil moisture balance methodology for recharge estimation , 2006 .

[39]  Yann Kerr,et al.  Soil moisture retrieval from space: the Soil Moisture and Ocean Salinity (SMOS) mission , 2001, IEEE Trans. Geosci. Remote. Sens..

[40]  George P. Petropoulos,et al.  Quantifying the prediction accuracy of a 1-D SVAT model at a range of ecosystems in the USA and Australia: evidence towards its use as a tool to study Earth's system interactions , 2015 .

[41]  Jeffrey D. Niemann,et al.  Evaluating the parameter identifiability and structural validity of a probability-distributed model for soil moisture , 2008 .