A Convolutional Neural Network Algorithm for Soil Moisture Prediction from Sentinel-1 SAR Images

Achieving the rational, optimal, and sustainable use of resources (water and soil) is vital to drink and feed 9.725 billion by 2050. Agriculture is the first source of food production, the biggest consumer of freshwater, and the natural filter of air purification. Hence, smart agriculture is a “ray of hope” in regard to food, water, and environmental security. Satellites and artificial intelligence have the potential to help agriculture flourish. This research is an essential step towards achieving smart agriculture. Prediction of soil moisture is important for determining when to irrigate and how much water to apply, to avoid problems associated with over- and under-watering. This also contributes to an increase in the number of areas being cultivated and, hence, agricultural productivity and air purification. Soil moisture measurement techniques, in situ, are point measurements, tedious, time-consuming, expensive, and labor-intensive. Therefore, we aim to provide a new approach to detect moisture content in soil without actually being in contact with it. In this paper, we propose a convolutional neural network (CNN) architecture that can predict soil moisture content over agricultural areas from Sentinel-1 images. The dual-pol (VV–VH) Sentinel-1 SAR data have being utilized (V = vertical, H = horizontal). The CNN model is composed of six convolutional layers, one max-pooling layer, one flatten layer, and one fully connected layer. The total number of Sentinel-1 images used for running CNN is 17,325 images. The best values of the performance metrics (coefficient of determination (R2=0.8664), mean absolute error (MAE=0.0144), and root mean square error (RMSE=0.0274)) have been achieved due to the use of Sigma naught VH and Sigma naught VV as input data to the CNN architecture (C). Results show that VV polarization is better than VH polarization for soil moisture retrieval, and that Sigma naught, Gamma naught, and Beta naught have the same influence on soil moisture estimation.

[1]  Fang Yuan,et al.  Building a SAR-Enabled Data Cube Capability in Australia Using SAR Analysis Ready Data , 2019, Data.

[2]  Fernando França da Cunha,et al.  Crop NDVI Monitoring Based on Sentinel 1 , 2019, Remote Sensing.

[3]  Marco Valtorta,et al.  The Effects of Data Quality on Machine Learning Algorithms , 2006, ICIQ.

[4]  Mehrez Zribi,et al.  Synergic Use of Sentinel-1 and Sentinel-2 Images for Operational Soil Moisture Mapping at High Spatial Resolution over Agricultural Areas , 2017, Remote. Sens..

[5]  Mayank D Mishra,et al.  Soil Moisture Estimation using Gravimetric Technique and FDR Probe Technique: A Comparative Analysis , 2014 .

[6]  S. O,et al.  Assessment of spatial uncertainty of heavy rainfall at catchment scale using a dense gauge network , 2019, Hydrology and Earth System Sciences.

[7]  Giovanni Nico,et al.  Accuracies of Soil Moisture Estimations Using a Semi-Empirical Model over Bare Soil Agricultural Croplands from Sentinel-1 SAR Data , 2020, Remote. Sens..

[8]  Mohammed Bennamoun,et al.  A Guide to Convolutional Neural Networks for Computer Vision , 2018, A Guide to Convolutional Neural Networks for Computer Vision.

[9]  A. Robock,et al.  The International Soil Moisture Network: a data hosting facility for global in situ soil moisture measurements , 2011 .

[10]  Mark Smith,et al.  Automatic Detection of Open and Vegetated Water Bodies Using Sentinel 1 to Map African Malaria Vector Mosquito Breeding Habitats , 2019, Remote. Sens..

[11]  J. Carreiras,et al.  Sentinel-1 observation frequency significantly increases burnt area detectability in tropical SE Asia , 2020, Environmental Research Letters.

[12]  Christoph Rüdiger,et al.  Sensitivity of Sentinel-1 Backscatter to Vegetation Dynamics: An Austrian Case Study , 2018, Remote. Sens..

[13]  Yun Zhang,et al.  Review and evaluation of remote sensing methods for soil-moisture estimation , 2011 .

[14]  Alberto Refice,et al.  Performance Analysis of Satellite Missions for Multi-Temporal SAR Interferometry , 2018, Sensors.

[15]  N. Fedoroff.  Food in a future of 10 billion , 2015, Agriculture & Food Security.

[16]  Yuzhong Shen,et al.  Quantifying Seagrass Distribution in Coastal Water with Deep Learning Models , 2020, Remote. Sens..

[17]  M. Tiwari,et al.  Soil Moisture Estimation using Sentinel-1 SAR Data and Land Surface Temperature in Panchmahal District, Gujarat State , 2021, International Journal of Environment and Geoinformatics.

[18]  Shoba Periasamy,et al.  Significance of dual polarimetric synthetic aperture radar in biomass retrieval: An attempt on Sentinel-1 , 2018, Remote Sensing of Environment.

[19]  Xiang Zhang,et al.  Multilayer Soil Moisture Mapping at a Regional Scale from Multisource Data via a Machine Learning Method , 2019, Remote. Sens..

[20]  Richard K. G. Do,et al.  Convolutional neural networks: an overview and application in radiology , 2018, Insights into Imaging.

[21]  Katarzyna Dabrowska-Zielinska,et al.  Soil Moisture in the Biebrza Wetlands Retrieved from Sentinel-1 Imagery , 2018, Remote. Sens..

[22]  Qi Gao,et al.  Synergetic Use of Sentinel-1 and Sentinel-2 Data for Soil Moisture Mapping at 100 m Resolution , 2017, Sensors.

[23]  Mehrez Zribi,et al.  Evaluation of Backscattering Models and Support Vector Machine for the Retrieval of Bare Soil Moisture from Sentinel-1 Data , 2019, Remote. Sens..

[24]  Antonino Maltese,et al.  Soil Water Content Assessment: Critical Issues Concerning the Operational Application of the Triangle Method , 2015, Sensors.

[25]  Matthias Drusch,et al.  Global Automated Quality Control of In Situ Soil Moisture Data from the International Soil Moisture Network , 2013 .

[26]  Kewei Cheng,et al.  Feature Selection , 2016, ACM Comput. Surv..

[27]  Daniel C. Yoder,et al.  SOILWATER SENSOR PERFORMANCE , 1998 .

[28]  Dalvinder Singh Grewal,et al.  A Critical Conceptual Analysis of Definitions of Artificial Intelligence as Applicable to Computer Engineering , 2014 .

[29]  Retrieving Surface Soil Moisture over Wheat-Covered Areas Using Data from Sentinel-1 and Sentinel-2 , 2021, Water.

[30]  Mehrez Zribi,et al.  Potential of Sentinel-1 Radar Data for the Assessment of Soil and Cereal Cover Parameters , 2017, Sensors.

[31]  Orhun Aydin,et al.  Artificial Intelligence Approaches , 2019, Geographic Information Science & Technology Body of Knowledge.

[32]  Birgit Kleinschmit,et al.  Comparing Sentinel-1 and -2 Data and Indices for Agricultural Land Use Monitoring , 2020, Remote. Sens..

[33]  Thuy Le Toan,et al.  Potential of Sentinel-1 Data for Monitoring Temperate Mixed Forest Phenology , 2018, Remote. Sens..

[34]  Tsegaye Tadesse,et al.  Soil Moisture Monitoring Using Remote Sensing Data and a Stepwise-Cluster Prediction Model: The Case of Upper Blue Nile Basin, Ethiopia , 2019, Remote. Sens..

[35]  H. Jones.  Irrigation scheduling: advantages and pitfalls of plant-based methods. , 2004, Journal of experimental botany.

[36]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[37]  Paul F. Whelan,et al.  Deep Learning in Texture Analysis and Its Application to Tissue Image Classification , 2017 .

[38]  Lars M. H. Ulander,et al.  Radiometric slope correction of synthetic-aperture radar images , 1996, IEEE Trans. Geosci. Remote. Sens..

[39]  Y. S. Rao,et al.  Dual polarimetric radar vegetation index for crop growth monitoring using sentinel-1 SAR data , 2020 .

[40]  Robert B. Fisher,et al.  Deep Learning for Coral Classification , 2017 .

[41]  S. Quiring,et al.  Estimating root zone soil moisture using near-surface observations from SMOS , 2013 .

[42]  Eric S. Kasischke,et al.  Remote monitoring of spatial and temporal surface soil moisture in fire disturbed boreal forest ecosystems with ERS SAR imagery , 2007 .

[43]  Yu Han,et al.  Integration of Time Series Sentinel-1 and Sentinel-2 Imagery for Crop Type Mapping over Oasis Agricultural Areas , 2020, Remote. Sens..

[44]  Amir Sadeghipour,et al.  Artificial intelligence in retina , 2018, Progress in Retinal and Eye Research.

[45]  Isaya Kisekka,et al.  Irrigation Scheduling Based on Soil Moisture Sensors and Evapotranspiration , 2015 .

[46]  Synergistic Use of Radar Sentinel-1 and Optical Sentinel-2 Imagery for Crop Mapping: A Case Study for Belgium , 2018, Remote Sensing.

[47]  Jakob J. van Zyl,et al.  A Time-Series Approach to Estimate Soil Moisture Using Polarimetric Radar Data , 2009, IEEE Transactions on Geoscience and Remote Sensing.