Mapping and prediction of soil organic carbon by an advanced geostatistical technique using remote sensing and terrain data

Mallik, Santanu; Bhowmik, Tridip; Mishra, Umesh; Paul, Niladri

doi:10.1080/10106049.2020.1815864

Cited by 24 publications

(18 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By dividing the data set, the method allows modelling the relationship between precipitation and co-variable and to capture the nonstationary of precipitation. The biggest advantage compared with classical kriging is that EBKR takes in consideration the semi variogram error (Santanu et al 2020). The weight of each semi variogram is calculated according to Bayes theorem (Yuanpei et al 2016).…”

Section: Ebkrmentioning

confidence: 99%

Comparison of spatial interpolation methods for estimating the precipitation distribution in Portugal

Antal

Guerreiro

Cheval

2021

Theor Appl Climatol

View full text Add to dashboard Cite

Precipitation has a strong and constant impact on different economic sectors, environment, and social activities all over the world. An increasing interest for monitoring and estimating the precipitation characteristics can be claimed in the last decades. However, in some areas the ground-based network is still sparse and the spatial data coverage insufficiently addresses the needs. In the last decades, different interpolation methods provide an efficient response for describing the spatial distribution of precipitation. In this study, we compare the performance of seven interpolation methods used for retrieving the mean annual precipitation over the mainland Portugal, as follows: local polynomial interpolation (LPI), global polynomial interpolation (GPI), radial basis function (RBF), inverse distance weighted (IDW), ordinary cokriging (OCK), universal cokriging (UCK) and empirical Bayesian kriging regression (EBKR). We generate the mean annual precipitation distribution using data from 128 rain gauge stations covering the period 1991 to 2000. The interpolation results were evaluated using cross-validation techniques and the performance of each method was evaluated using mean error (ME), mean absolute error (MAE), root mean square error (RMSE), Pearson's correlation coefficient (R) and Taylor diagram. The results indicate that EBKR performs the best spatial distribution. In order to determine the accuracy of spatial distribution generated by the spatial interpolation methods, we calculate the prediction standard error (PSE). The PSE result of EBKR prediction over mainland Portugal increases form south to north.

show abstract

Section: Ebkrmentioning

confidence: 99%

Comparison of spatial interpolation methods for estimating the precipitation distribution in Portugal

Antal

Guerreiro

Cheval

2021

Theor Appl Climatol

View full text Add to dashboard Cite

show abstract

“…Arti cial neural network (ANN) is a non-linear supervised deep learning method, which tends to mimic the human brain and biological nervous system (Amanollahi and Ausati, 2020;Ordieres et al, 2005;Yao et al, 2012). The capability of learning a complex relationship problem between input and output parameters makes the ANN model more exible and more usable in many multidisciplinary elds (Emamgholizadeh et al 2017;Mallik et al 2020).…”

Section: Arti Cial Neural Network (Ann)mentioning

confidence: 99%

Prediction and assessment of change in PM2.5 during COVID-19 lockdown using remote sensing and deep learning approach: A case study of Kanpur city

Mallik

Soni²,

Podder

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

In the last few months, the corona virus crises have changed the world completely. In India, looking at the horrific condition and rate of increase of COVID-19 positive cases, the central government has imposed strict lockdown from dated March 24 throughout the country. At the same time, with citizens quarantined and grinding halt in industrial activities has led to some inadvertent benefits and change in air pollution level is one of them. The present study is undertaken with an aim to predict and assess the change in PM2.5 level of the Kanpur city using MODIS Aerosol Optical Depth (AOD) data and meteorological parameters during various stages of COVID-19 lockdown. Subsequently, four different methods such as linear regression (LR), multilinear regression (MLR), artificial neural network (ANN), and a hybrid method were used and compared for the prediction of PM2.5. The best prediction method was further used for the spatial mapping of PM2.5 at different stages of lockdown (pre-lockdown, during lockdown and post lockdown). The result of cross-validation shows that the hybrid method i.e. (MLR+ANN) outperforms all other methods and gives the highest coefficient of determination R2 value of 0.961 followed by ANN, MLR, and LR with 0.895, 0.246, 0.016. The spatial mapping of PM2.5 during the lockdown shows a significant reduction of 26% in PM2.5 concentration in comparison to pre lockdown. The methodology developed from the current study can also be used in other regions for predicting and analyzing the spatio-temporal variation of PM2.5.

show abstract

“…Several studies have reported that hybrid models improve prediction accuracy (Dai et al 2014;Mirzaee et al 2016;Tziachris et al 2019;Matinfar et al 2021). However, few studies have been conducted on the performance of EBKRP over machine-learning approaches (Requia et al 2019;Mallik et al 2020). Speci cally, no well-documented studies have reported the prediction performance of EBKRP, RF, and the hybrid methods of RF-EBKRP for the spatial prediction of PTEs in the soil.…”

Section: Introductionmentioning

confidence: 99%

A machine learning and geostatistical hybrid method to improve spatial prediction accuracy of soil potentially toxic elements

Molla

Zhang

Zuo

et al. 2022

Stoch Environ Res Risk Assess

View full text Add to dashboard Cite

Effective environmental management and contamination remediation require accurate spatial variation and prediction of potentially toxic elements (PTEs) in the soil. However, no single method has been developed to predict soil PTEs accurately. This study evaluated the ability of the advanced geostatistical method of empirical Bayesian kriging regression prediction (EBKRP), machine learning algorithms of random forest (RF), and the combination of RF and EBKRP to predict and map soil PTE content. The root mean square error (RMSE), mean absolute percentage error (MAPE), and coe cient of determination (R 2 ) were used to assess model prediction performance. As identi ed by RF, soil organic carbon, soil organic matter, total (nitrogen, phosphorus, and potassium), slope, and elevation were ranked as signi cant covariates to improve the prediction accuracy of PTEs in greenspace soil. Results showed that the RF method improved the prediction accuracy over the EBKRP method, and the improvement was from 24-40% for RMSE, 41-210% for R 2 , and 18-35% for MAPE. However, hybrid methods (RF-EBKRP) increased accuracy by comparing the individually predicted models with 345% and 33% in EBKRP and RF, based on R 2 , respectively. Moreover, the RF-EBKRP method decreased MAPE by 5.33-18.69% and 0.48-12.33% on average than EBKRP and RF, respectively.In conclusion, in addition to incorporating covariates into the models, combining kriging residuals with the machine learning method (RF-EBKRP) resulted in a promising approach for improving the distribution accuracy and mapping of PTEs in the soil.

show abstract

Mapping and prediction of soil organic carbon by an advanced geostatistical technique using remote sensing and terrain data

Cited by 24 publications

References 36 publications

Comparison of spatial interpolation methods for estimating the precipitation distribution in Portugal

Comparison of spatial interpolation methods for estimating the precipitation distribution in Portugal

Prediction and assessment of change in PM2.5 during COVID-19 lockdown using remote sensing and deep learning approach: A case study of Kanpur city

A machine learning and geostatistical hybrid method to improve spatial prediction accuracy of soil potentially toxic elements

Contact Info

Product

Resources

About