Spatial prediction of susceptibility to gully erosion in Jainti River basin, Eastern India: a comparison of information value and logistic regression models

Hembram, Tusar Kanti; Paul, Goutam; Saha, Sunil

doi:10.1007/s40808-018-0560-8

Cited by 40 publications

(27 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the RF model is a better model for the prediction of GES (Table 6) for this basin compared to the other models. The findings also showed that the result of the tree-based ensemble methods has a better accuracy than the statistical models used in this region [23,24,87]. Our results are rational as the tree-based machine learning algorithms minimized bias, variance, and overfitting issues in GES modeling.…”

Section: Models Comparisonssupporting

confidence: 63%

“…A total of 120 gullies were identified in the study area. Of the 120 gullies, 84 (70%) gullies were randomly selected for model preparation, and the remaining 36 (30%) gullies were used for model validation ( Figure 3) based on previous literature [20,23,24]. Representative gully images are shown in Figure 1.…”

Section: Preparing the Gully Inventory Map (Gim)mentioning

confidence: 99%

“…In the last two decades, the use of remote sensing data to predict gully susceptibility has increased enormously [17]. Presently, combined with remote sensing and GIS, different probabilistic, knowledge-driven and machine learning methods are being used to generate GESM, such as bivariate statistics (BS) [1], weights-of-evidence (WoE) [18][19][20], logistic regression (LR) [21][22][23][24], information value (IV) [22], random forest (RF) [25], bivariate statistical models [26], maximum entropy (ME) [27], frequency ratio (FR) [26,28], analytical hierarchy processes (AHP) [29], artificial neural network (ANN) [11,27], Functional tree (FT), Naïve Bayes tree (NBTree) [12], support vector machine (SVM) [27] and boosted regression trees (BRT) [11]. In the present research, tree-based machine learning algorithms, namely the Random Forest (RF), Gradient Boosted Regression Tree (GBRT), Naïve Bayes Tree (NBTree), and Tree Ensemble (TE) models were used to model the gully erosion susceptibility.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Machine Learning-Based Gully Erosion Susceptibility Mapping: A Case Study of Eastern India

Saha

Arabameri

Blaschke

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

Gully erosion is a form of natural disaster and one of the land loss mechanisms causing severe problems worldwide. This study aims to delineate the areas with the most severe gully erosion susceptibility (GES) using the machine learning techniques Random Forest (RF), Gradient Boosted Regression Tree (GBRT), Naïve Bayes Tree (NBT), and Tree Ensemble (TE). The gully inventory map (GIM) consists of 120 gullies. Of the 120 gullies, 84 gullies (70%) were used for training and 36 gullies (30%) were used to validate the models. Fourteen gully conditioning factors (GCFs) were used for GES modeling and the relationships between the GCFs and gully erosion was assessed using the weight-of-evidence (WofE) model. The GES maps were prepared using RF, GBRT, NBT, and TE and were validated using area under the receiver operating characteristic (AUROC) curve, the seed cell area index (SCAI) and five statistical measures including precision (PPV), false discovery rate (FDR), accuracy, mean absolute error (MAE), and root mean squared error (RMSE). Nearly 7% of the basin has high to very high susceptibility for gully erosion. Validation results proved the excellent ability of these models to predict the GES. Of the analyzed models, the RF (AUROC = 0.96, PPV = 1.00, FDR = 0.00, accuracy = 0.87, MAE = 0.11, RMSE = 0.19 for validation dataset) is accurate enough for modeling and better suited for GES modeling than the other models. Therefore, the RF model can be used to model the GES areas not only in this river basin but also in other areas with the same geo-environmental conditions.

show abstract

Section: Models Comparisonssupporting

confidence: 63%

Section: Preparing the Gully Inventory Map (Gim)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning-Based Gully Erosion Susceptibility Mapping: A Case Study of Eastern India

Saha

Arabameri

Blaschke

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Machine learning algorithms cannot express the relationships among the influencing factor’s internal levels and the occurrence of schistosomiasis. IV does not consider differences in the weight contribution of influencing factors [ 24 ]. The higher success rate for the coupled model is that it considers the internal level of influencing factors and the weight of different influencing factors in relationship to schistosomiasis [ 25 ].…”

Section: Discussionmentioning

confidence: 99%

Identification of the high-risk area for schistosomiasis transmission in China based on information value and machine learning: a newly data-driven modeling attempt

Gong

Zhu

et al. 2021

Infect Dis Poverty

View full text Add to dashboard Cite

Background Schistosomiasis control is striving forward to transmission interruption and even elimination, evidence-lead control is of vital importance to eliminate the hidden dangers of schistosomiasis. This study attempts to identify high risk areas of schistosomiasis in China by using information value and machine learning. Methods The local case distribution from schistosomiasis surveillance data in China between 2005 and 2019 was assessed based on 19 variables including climate, geography, and social economy. Seven models were built in three categories including information value (IV), three machine learning models [logistic regression (LR), random forest (RF), generalized boosted model (GBM)], and three coupled models (IV + LR, IV + RF, IV + GBM). Accuracy, area under the curve (AUC), and F1-score were used to evaluate the prediction performance of the models. The optimal model was selected to predict the risk distribution for schistosomiasis. Results There is a more prone to schistosomiasis epidemic provided that paddy fields, grasslands, less than 2.5 km from the waterway, annual average temperature of 11.5–19.0 °C, annual average rainfall of 1000–1550 mm. IV + GBM had the highest prediction effect (accuracy = 0.878, AUC = 0.902, F1 = 0.920) compared with the other six models. The results of IV + GBM showed that the risk areas are mainly distributed in the coastal regions of the middle and lower reaches of the Yangtze River, the Poyang Lake region, and the Dongting Lake region. High-risk areas are primarily distributed in eastern Changde, western Yueyang, northeastern Yiyang, middle Changsha of Hunan province; southern Jiujiang, northern Nanchang, northeastern Shangrao, eastern Yichun in Jiangxi province; southern Jingzhou, southern Xiantao, middle Wuhan in Hubei province; southern Anqing, northwestern Guichi, eastern Wuhu in Anhui province; middle Meishan, northern Leshan, and the middle of Liangshan in Sichuan province. Conclusions The risk of schistosomiasis transmission in China still exists, with high-risk areas relatively concentrated in the coastal regions of the middle and lower reaches of the Yangtze River. Coupled models of IV and machine learning provide for effective analysis and prediction, forming a scientific basis for evidence-lead surveillance and control. Graphic Abstract

show abstract

“…It is difficult to calculate the weight of environmental factors accurately when predicting epidemic disease risk areas with a single risk-assessment model. Risk prediction combining an information quantity model and a logistic regression model ( I+LR ) has been successfully applied in risk assessment of geological disasters [ 26 ]; however, this approach has not been applied to HFRS epidemic risk prediction previously, as we have done here.…”

Section: Data Collectionmentioning

confidence: 99%

Prediction of hot spot areas of hemorrhagic fever with renal syndrome in Hunan Province based on an information quantity model and logistical regression model

Chen

Liu

et al. 2020

PLoS Negl Trop Dis

View full text Add to dashboard Cite

Background China’s “13th 5-Year Plan” (2016–2020) for the prevention and control of sudden acute infectious diseases emphasizes that epidemic monitoring and epidemic focus surveys in key areas are crucial for strengthening national epidemic prevention and building control capacity. Establishing an epidemic hot spot areas and prediction model is an effective means of accurate epidemic monitoring and surveying. Objective: This study predicted hemorrhagic fever with renal syndrome (HFRS) epidemic hot spot areas, based on multi-source environmental variable factors. We calculated the contribution weight of each environmental factor to the morbidity risk, obtained the spatial probability distribution of HFRS risk areas within the study region, and detected and extracted epidemic hot spots, to guide accurate epidemic monitoring as well as prevention and control. Methods: We collected spatial HFRS data, as well as data on various types of natural and human social activity environments in Hunan Province from 2010 to 2014. Using the information quantity method and logistic regression modeling, we constructed a risk-area-prediction model reflecting the epidemic intensity and spatial distribution of HFRS. Results: The areas under the receiver operating characteristic curve of training samples and test samples were 0.840 and 0.816. From 2015 to 2019, HRFS case site verification showed that more than 82% of the cases occurred in high-risk areas. Discussion This research method could accurately predict HFRS hot spot areas and provided an evaluation model for Hunan Province. Therefore, this method could accurately detect HFRS epidemic high-risk areas, and effectively guide epidemic monitoring and surveyance.

show abstract

Spatial prediction of susceptibility to gully erosion in Jainti River basin, Eastern India: a comparison of information value and logistic regression models

Cited by 40 publications

References 42 publications

Machine Learning-Based Gully Erosion Susceptibility Mapping: A Case Study of Eastern India

Machine Learning-Based Gully Erosion Susceptibility Mapping: A Case Study of Eastern India

Identification of the high-risk area for schistosomiasis transmission in China based on information value and machine learning: a newly data-driven modeling attempt

Prediction of hot spot areas of hemorrhagic fever with renal syndrome in Hunan Province based on an information quantity model and logistical regression model

Contact Info

Product

Resources

About