Accuracies of Soil Moisture Estimations Using a Semi-Empirical Model over Bare Soil Agricultural Croplands from Sentinel-1 SAR Data

Hoskera, Anil Kumar; Nico, Giovanni; Ahmed, M. Irshad; Whitbread, Anthony

doi:10.3390/rs12101664

Cited by 17 publications

(8 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We can now say with high confidence that: (1) VV polarization is more sensitive than VH polarization for soil moisture retrieval; similar results have been found by [19][20][21][22][23]. (2) The combination of VV and VH polarization has resulted in improvement in the prediction of soil moisture from Sentinel-1 images, our result agree with [24][25][26]. (3) The best inputs to the CNN to retrieve soil moisture from Sentinel-1 images are Sigma0_VH and Sigma0_VV, or Gamma0_VH and Gamma0_VV, or Beta0_VH and Beta0_VV.…”

Section: Comparison Between Cnn Architecture (𝐶 𝐼𝐼 ) and Cnn Architecture (𝐶 𝐼𝐼𝐼 )supporting

confidence: 88%

“…(2) The combination of VV and VH polarization has resulted in improvement in the prediction of soil moisture from Sentinel-1 images, our result agree with [24][25][26]. (3) The best inputs to the CNN to retrieve soil moisture from Sentinel-1 images are Sigma0_VH and Sigma0_VV, or Gamma0_VH and Gamma0_VV, or Beta0_VH and Beta0_VV.…”

Section: Comparison Between Cnn Architecture (𝐶 𝐼𝐼 ) and Cnn Architecture (𝐶 𝐼𝐼𝐼 )supporting

confidence: 77%

“…VV polarization was more sensitive for soil moisture retrieval from Sentinel-1 data as compared to VH polarization [21][22][23]. Several studies have indicated that the accuracy of the soil moisture estimates improved when using both VV and VH polarization, instead of only VV or VH polarization [24][25][26].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

2021

View full text Add to dashboard Cite

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.

show abstract

Section: Comparison Between Cnn Architecture (𝐶 𝐼𝐼 ) and Cnn Architecture (𝐶 𝐼𝐼𝐼 )supporting

confidence: 88%

Section: Comparison Between Cnn Architecture (𝐶 𝐼𝐼 ) and Cnn Architecture (𝐶 𝐼𝐼𝐼 )supporting

confidence: 77%

See 1 more Smart Citation

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

2021

View full text Add to dashboard Cite

show abstract

“…Th radiation correction for the four bands was performed using the ENVI 5.3 software to convert the digital number (DN) of the images to the surface spectral reflectance. The atmospheric correction was conducted using the FLAASH Atmospheric Correction toolbox using the ENVI software [44,47,[52][53][54][55]. After atmospheric correction, the images were geo-referenced based on 25 ground control points.…”

Section: Gf-1 Datamentioning

confidence: 99%

High-Precision Soil Moisture Mapping Based on Multi-Model Coupling and Background Knowledge, Over Vegetated Areas Using Chinese GF-3 and GF-1 Satellite Data

Han

Wang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

This paper proposes a combined approach comprising a set of methods for the high-precision mapping of soil moisture in a study area located in Jiangsu Province of China, based on the Chinese C-band synthetic aperture radar data of GF-3 and high spatial-resolution optical data of GF-1, in situ experimental datasets and background knowledge. The study was conducted in three stages: First, in the process of eliminating the effect of vegetation canopy, an empirical vegetation water content model and a water cloud model with localized parameters were developed to obtain the bare soil backscattering coefficient. Second, four commonly used models (advanced integral equation model (AIEM), look-up table (LUT) method, Oh model, and the Dubois model) were coupled to acquire nine soil moisture retrieval maps and algorithms. Finally, a simple and effective optimal solution method was proposed to select and combine the nine algorithms based on classification strategies devised using three types of background knowledge. A comprehensive evaluation was carried out on each soil moisture map in terms of the root-mean-square-error (RMSE), Pearson correlation coefficient (PCC), mean absolute error (MAE), and mean bias (bias). The results show that for the nine individual algorithms, the estimated model constructed using the AIEM (mv1) was significantly more accurate than those constructed using the other models (RMSE = 0.0321 cm³/cm³, MAE = 0.0260 cm³/cm³, and PCC = 0.9115), followed by the Oh model (m_v5) and LUT inversion method under HH polarization (mv2). Compared with the independent algorithms, the optimal solution methods have significant advantages; the soil moisture map obtained using the classification strategy based on the percentage content of clay was the most satisfactory (RMSE = 0.0271 cm³/cm³, MAE = 0.0225 cm³/cm³, and PCC = 0.9364). This combined method could not only effectively integrate the optical and radar satellite data but also couple a variety of commonly used inversion models, and at the same time, background knowledge was introduced into the optimal solution method. Thus, we provide a new method for the high-precision mapping of soil moisture in areas with a complex underlying surface.

show abstract

“…The backscatter of VH polarization can partially improve the detection of low vegetation or crop [49], while the VV polarization can be more sensitive to soil variations [50], although these considerations should be further investigated for buildings and infrastructures.…”

mentioning

confidence: 99%

Land Consumption Monitoring with SAR Data and Multispectral Indices

et al. 2021

View full text Add to dashboard Cite

Land consumption is the increase in artificial land cover, which is a major issue for environmental sustainability. In Italy, the Italian Institute for Environmental Protection and Research (ISPRA) and National System for Environmental Protection (SNPA) have the institutional duty to monitor land consumption yearly, through the photointerpretation of high-resolution images. This study intends to develop a methodology in order to produce maps of land consumption, by the use of the semi-automatic classification of multitemporal images, to reduce the effort of photointerpretation in detecting real changes. The developed methodology uses vegetation indices calculated over time series of images and decision rules. Three variants of the methodology were applied to detect the changes that occurred in Italy between the years 2018 and 2019, and the results were validated using ISPRA official data. The results show that the produced maps include large commission errors, but thanks to the developed methodology, the area to be photointerpreted was reduced to 7,300 km2 (2.4 % of Italian surface). The third variant of the methodology provided the highest detection of changes: 70.4% of the changes larger than 100 m2 (the pixel size) and over 84.0% of changes above 500 m2. Omissions are mainly related to single pixel changes, while larger changes are detected by at least one pixel in most of the cases. In conclusion, the developed methodology can improve the detection of land consumption, focusing photointerpretation work over selected areas detected automatically.

show abstract

Accuracies of Soil Moisture Estimations Using a Semi-Empirical Model over Bare Soil Agricultural Croplands from Sentinel-1 SAR Data

Cited by 17 publications

References 30 publications

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

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

High-Precision Soil Moisture Mapping Based on Multi-Model Coupling and Background Knowledge, Over Vegetated Areas Using Chinese GF-3 and GF-1 Satellite Data

Land Consumption Monitoring with SAR Data and Multispectral Indices

Contact Info

Product

Resources

About