Soil electrical conductivity imaging using a neural network-based forward solver: Applied to large-scale Bayesian electromagnetic inversion

2020 ◽  
Vol 176 ◽  
pp. 104012 ◽  
Author(s):  
Davood Moghadas ◽  
Ahmad A. Behroozmand ◽  
Anders Vest Christiansen
Keyword(s):  
Neural Network ◽  
Electrical Conductivity ◽  
Large Scale ◽  
Soil Electrical Conductivity ◽  
Conductivity Imaging

scholarly journals Prediction Model of Soil Electrical Conductivity Based on ELM Optimized by Bald Eagle Search Algorithm

2021 ◽  
Vol 25 (2) ◽  
pp. 50-56
Author(s):  
Ying Huang ◽  
◽  
Hao Jiang ◽  
Weixing Wang ◽  
Daozong Sun ◽  
...  
Keyword(s):  
Neural Network ◽  
Electrical Conductivity ◽  
Prediction Model ◽  
Bald Eagle ◽  
Support Vector ◽  
Particle Swarm Algorithm ◽  
Good Prediction ◽  
Soil Electrical Conductivity ◽  
Proposed Model ◽  
Soil Conductivity

Soil electrical conductivity is one of the indispensable and important parameters in fine agriculture management, and a suitable soil electrical conductivity can promote good plant growth. Prediction model of soil electrical conductivity is constructed to effectively obtain the conductivity values of soil, which can provide a reference basis for irrigation and fertilization management and prediction evaluation in fine agriculture. Prediction model of soil electrical conductivity based on extreme learning machine (ELM) optimized by bald eagle search (BES) algorithm is proposed in this paper. In the prediction model, the input weights and bias values of the ELM network were optimized using the BES algorithm, and the performance of the model was evaluated with parameters such as mean square error (MSE), coefficient of determination (R^2). Also, the correlations of parameters such as soil temperature, moisture content, pH, and water potential in the soil conductivity prediction model were determined using the exploratory data analysis (EDA) and HeatMap heat map tools. Finally, the proposed model was compared with back propagation neural network (BP), radial basis function networks (RBF), support vector machine (SVM), gated recurrent neural network (GRNN), long short-term memory (LSTM), particle swarm algorithm (PSO) optimization ELM, genetic algorithm (GA) optimized ELM prediction model. The experimental results showed that MSE, R^2 of the proposed model are 4.09 and 0.941, which are better than the other models. Also the results verified the effectiveness of the proposed method, which is a feasible prediction method to guide the irrigation and fertilization management in fine agriculture, because of its good prediction effect on soil conductivity.

scholarly journals Regional calibration and electromagnetic conductivity imaging for assessing the dynamics of soil salinity

2021 ◽  
Author(s):  
Maria Catarina Paz ◽  
Mohammad Farzamian ◽  
Ana Marta Paz ◽  
Nádia Luísa Castanheira ◽  
Maria Conceição Gonçalves ◽  
...  
Keyword(s):  
Electrical Conductivity ◽  
Soil Salinity ◽  
Sea Water ◽  
Agricultural System ◽  
Soil Electrical Conductivity ◽  
Prediction Ability ◽  
Calibration Equation ◽  
Transient Nature ◽  
Salinity Levels ◽  
Conductivity Imaging

<p>Electromagnetic conductivity imaging (EMCI) is a state-of-the-art methodology for soil salinity assessment over large areas. It involves the following rationale: (1) use of the electromagnetic induction (EMI) geophysical technique to measure the soil apparent electrical conductivity (EC<sub>a</sub>, mS m<sup>−1</sup>) over an area; (2) inversion of EC<sub>a</sub> to obtain EMCI, which provides the spatial distribution of the soil electrical conductivity (σ, mS m<sup>−1</sup>); (3) calibration process consisting of a regression between σ and the electrical conductivity of the saturated soil paste extract (EC<sub>e</sub>, dS m<sup>−1</sup>), used as a proxy for soil salinity; and (4) conversion of EMCI into salinity maps using the obtained calibration equation.</p><p>In this study, we applied EMCI and a regional calibration in Lezíria Grande de Vila Franca de Xira, located in Portugal. The study area is an important agricultural system where soil faces the risk of salinization due to climate change, as the level and salinity of groundwater are likely to increase as a result of the rise of the sea water level and consequently of the estuary. These changes can also affect the salinity of the irrigation water which is collected upstream of the estuary.</p><p>EMI surveys and soil sampling were carried out between May 2017 and October 2018 at four locations with different salinity levels across the study area. A regional calibration was developed and its ability to predict EC<sub>e</sub> from EMCI was evaluated. The validation analysis showed that EC<sub>e</sub> was predicted with a root mean square error of 3.14 dS m<sup>−1</sup> in a range of 52.35 dS m<sup>−1</sup>, slightly overestimated (−1.23 dS m<sup>−1</sup>), with a strong Lin’s concordance correlation coefficient of 0.94 and high linearity between measured and predicted data (R<sup>2</sup> = 0.88). It was also observed that the prediction ability of the regional calibration is more influenced by spatial variability of data than temporal variability of data.</p><p>Because of the transient nature of data, it was also possible to perform a preliminary qualitative analysis of soil salinity dynamics in the study area, revealing salinity fluctuations related to the input of salts and water either through irrigation, precipitation, or level and salinity of groundwater.</p>

Economic benefit of shale gas exploitation based on back propagation neural network

2020 ◽  
Vol 39 (6) ◽  
pp. 8823-8830
Author(s):  
Jiafeng Li ◽  
Hui Hu ◽  
Xiang Li ◽  
Qian Jin ◽  
Tianhao Huang
Keyword(s):  
Neural Network ◽  
Shale Gas ◽  
Bp Neural Network ◽  
Large Scale ◽  
Linear Prediction ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Economic Benefits ◽  
Gas Well ◽  
Well Production

Under the influence of COVID-19, the economic benefits of shale gas development are greatly affected. With the large-scale development and utilization of shale gas in China, it is increasingly important to assess the economic impact of shale gas development. Therefore, this paper proposes a method for predicting the production of shale gas reservoirs, and uses back propagation (BP) neural network to nonlinearly fit reservoir reconstruction data to obtain shale gas well production forecasting models. Experiments show that compared with the traditional BP neural network, the proposed method can effectively improve the accuracy and stability of the prediction. There is a nonlinear correlation between reservoir reconstruction data and gas well production, which does not apply to traditional linear prediction methods

Non-Blind Image Deconvolution Based on “Ringing” Removal Using Convolutional Neural Network

2020 ◽  
Vol 2020 (10) ◽  
pp. 181-1-181-7
Author(s):  
Takahiro Kudo ◽  
Takanori Fujisawa ◽  
Takuro Yamaguchi ◽  
Masaaki Ikehara
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Large Scale ◽  
Blind Deconvolution ◽  
Training Dataset ◽  
Image Deconvolution ◽  
Classic Problem ◽  
Key Points ◽  
Blind Image

Image deconvolution has been an important issue recently. It has two kinds of approaches: non-blind and blind. Non-blind deconvolution is a classic problem of image deblurring, which assumes that the PSF is known and does not change universally in space. Recently, Convolutional Neural Network (CNN) has been used for non-blind deconvolution. Though CNNs can deal with complex changes for unknown images, some CNN-based conventional methods can only handle small PSFs and does not consider the use of large PSFs in the real world. In this paper we propose a non-blind deconvolution framework based on a CNN that can remove large scale ringing in a deblurred image. Our method has three key points. The first is that our network architecture is able to preserve both large and small features in the image. The second is that the training dataset is created to preserve the details. The third is that we extend the images to minimize the effects of large ringing on the image borders. In our experiments, we used three kinds of large PSFs and were able to observe high-precision results from our method both quantitatively and qualitatively.

Sign in / Sign up

Export Citation Format

Share Document