Global-change controls on soil-carbon accumulation and loss in coastal vegetated ecosystems

Nature Geoscience, Journal Year: 2019, Volume and Issue: 12(9), P. 685 - 692

Published: Aug. 30, 2019

Language: Английский

---

Prediction Success of Machine Learning Methods for Flash Flood Susceptibility Mapping in the Tafresh Watershed, Iran

Sustainability, Journal Year: 2019, Volume and Issue: 11(19), P. 5426 - 5426

Published: Sept. 30, 2019

Floods are some of the most destructive and catastrophic disasters worldwide. Development management plans needs a deep understanding likelihood magnitude future flood events. The purpose this research was to estimate flash susceptibility in Tafresh watershed, Iran, using five machine learning methods, i.e., alternating decision tree (ADT), functional (FT), kernel logistic regression (KLR), multilayer perceptron (MLP), quadratic discriminant analysis (QDA). A geospatial database including 320 historical events constructed eight geo-environmental variables—elevation, slope, slope aspect, distance from rivers, average annual rainfall, land use, soil type, lithology—were used as influencing factors. Based on variety performance metrics, it is revealed that ADT method dominant over other methods. FT ranked second-best method, followed by KLR, MLP, QDA. Given few differences between goodness-of-fit prediction success we concluded all these machine-learning-based models applicable for mapping areas protect societies devastating floods.

Language: Английский

---

Performance Evaluation of Machine Learning Methods for Forest Fire Modeling and Prediction

Symmetry, Journal Year: 2020, Volume and Issue: 12(6), P. 1022 - 1022

Published: June 17, 2020

Predicting and mapping fire susceptibility is a top research priority in fire-prone forests worldwide. This study evaluates the abilities of Bayes Network (BN), Naïve (NB), Decision Tree (DT), Multivariate Logistic Regression (MLP) machine learning methods for prediction across Pu Mat National Park, Nghe An Province, Vietnam. The modeling methodology was formulated based on processing information from 57 historical fires set nine spatially explicit explanatory variables, namely elevation, slope degree, aspect, average annual temperate, drought index, river density, land cover, distance roads residential areas. Using area under receiver operating characteristic curve (AUC) seven other performance metrics, models were validated terms their to elucidate general behaviors Park predict future fires. Despite few differences between AUC values, BN model with an value 0.96 dominant over predicting second best DT (AUC = 0.94), followed by NB 0.939), MLR 0.937) models. Our robust analysis demonstrated that these are sufficiently response training validation datasets change. Further, results revealed moderate high levels susceptibilities associated ~19% where human activities numerous. resultant maps provide basis developing more efficient fire-fighting strategies reorganizing policies favor sustainable management forest resources.

Language: Английский

---

Soft Computing Ensemble Models Based on Logistic Regression for Groundwater Potential Mapping

Applied Sciences, Journal Year: 2020, Volume and Issue: 10(7), P. 2469 - 2469

Published: April 3, 2020

Groundwater potential maps are one of the most important tools for management groundwater storage resources. In this study, we proposed four ensemble soft computing models based on logistic regression (LR) combined with dagging (DLR), bagging (BLR), random subspace (RSSLR), and cascade generalization (CGLR) techniques mapping in Dak Lak Province, Vietnam. A suite well yield data twelve geo-environmental factors (aspect, elevation, slope, curvature, Sediment Transport Index, Topographic Wetness flow direction, rainfall, river density, soil, land use, geology) were used generating training validation datasets required building models. Based area under receiver operating characteristic curve (AUC) several other methods (negative predictive value, positive root mean square error, accuracy, sensitivity, specificity, Kappa), it was revealed that all learning successful enhancing performance base LR model. The DLR model (AUC = 0.77) identifying zones study area, followed by RSSLR 0.744), BLR 0.735), CGLR 0.715), single 0.71), respectively. developed resulting can assist decision-makers development effective adaptive plans.

Language: Английский

---

Microbial diversity and ecological interactions of microorganisms in the mangrove ecosystem: Threats, vulnerability, and adaptations

Environmental Science and Pollution Research, Journal Year: 2022, Volume and Issue: 29(22), P. 32467 - 32512

Published: Feb. 19, 2022

Language: Английский

---

A Review of Spectral Indices for Mangrove Remote Sensing

Remote Sensing, Journal Year: 2022, Volume and Issue: 14(19), P. 4868 - 4868

Published: Sept. 29, 2022

Mangrove ecosystems provide critical goods and ecosystem services to coastal communities contribute climate change mitigation. Over four decades, remote sensing has proved its usefulness in monitoring mangrove on a broad scale, over time, at lower cost than field observation. The increasing use of spectral indices led an expansion the geographical context studies from local-scale intercontinental global analyses past 20 years. In sensing, numerous derived multiple bands remotely sensed data have been developed used for mangroves. this paper, we review range produced utilised between 1996 2021. Our findings reveal that variety aspects but excluded identification species. included are extent, distribution, above ground parameters (e.g., carbon density, biomass, canopy height, estimations LAI), changes aforementioned time. Normalised Difference Vegetation Index (NDVI) was found be most widely applied index mangroves, 82% reviewed, followed by Enhanced (EVI) 28% studies. Development application potential cover characterisation increased (currently 6 published), NDVI remains popular sensing. Ultimately, identify limitations gaps current suggest some future directions under topic connection time series imagery fusion optical sensors digital era.

Language: Английский

---

Significance of Avicennia Marina in the Arabian Gulf Environment: A Review

Wetlands, Journal Year: 2025, Volume and Issue: 45(1)

Published: Jan. 1, 2025

Language: Английский

---

Groundwater Potential Mapping Combining Artificial Neural Network and Real AdaBoost Ensemble Technique: The DakNong Province Case-study, Vietnam

International Journal of Environmental Research and Public Health, Journal Year: 2020, Volume and Issue: 17(7), P. 2473 - 2473

Published: April 4, 2020

: The main aim of this study is to assess groundwater potential the DakNong province, Vietnam, using an advanced ensemble machine learning model (RABANN) that integrates Artificial Neural Networks (ANN) with RealAdaBoost (RAB) technique. For study, twelve conditioning factors and wells yield data was used create training testing datasets for development validation RABANN model. Area Under Receiver Operating Characteristic (ROC) curve (AUC) several statistical performance measures were validate compare single ANN Results studies showed both models performed well in phase assessing (AUC ≥ 0.7), whereas = 0.776) outperformed 0.699) phase. This demonstrated RAB technique successful improving By making minor adjustment input data, developed can be adapted mapping other regions countries toward more efficient water resource management. present would helpful condition area thus solving borne disease related health problem population.

Language: Английский

---

Landslide Susceptibility Mapping Using Machine Learning Algorithms and Remote Sensing Data in a Tropical Environment

International Journal of Environmental Research and Public Health, Journal Year: 2020, Volume and Issue: 17(14), P. 4933 - 4933

Published: July 8, 2020

We used AdaBoost (AB), alternating decision tree (ADTree), and their combination as an ensemble model (AB-ADTree) to spatially predict landslides in the Cameron Highlands, Malaysia. The models were trained with a database of 152 compiled using Synthetic Aperture Radar Interferometry, Google Earth images, field surveys, 17 conditioning factors (slope, aspect, elevation, distance road, river, proximity fault, road density, river normalized difference vegetation index, rainfall, land cover, lithology, soil types, curvature, profile stream power topographic wetness index). carried out validation process area under receiver operating characteristic curve (AUC) several parametric non-parametric performance metrics, including positive predictive value, negative sensitivity, specificity, accuracy, root mean square error, Friedman Wilcoxon sign rank tests. AB (AUC = 0.96) performed better than AB-ADTree 0.94) successfully outperformed ADTree 0.59) predicting landslide susceptibility. Our findings provide insights into development more efficient accurate that can be by makers land-use managers mitigate hazards.

Language: Английский

---

Deep learning neural networks for spatially explicit prediction of flash flood probability

Geoscience Frontiers, Journal Year: 2020, Volume and Issue: 12(3), P. 101076 - 101076

Published: Dec. 17, 2020

Flood probability maps are essential for a range of applications, including land use planning and developing mitigation strategies early warning systems. This study describes the potential application two architectures deep learning neural networks, namely convolutional networks (CNN) recurrent (RNN), spatially explicit prediction mapping flash flood probability. To develop validate predictive models, geospatial database that contained records historical events geo-environmental characteristics Golestan Province in northern Iran was constructed. The step-wise weight assessment ratio analysis (SWARA) employed to investigate spatial interplay between floods different influencing factors. CNN RNN models were trained using SWARA weights validated receiver operating technique. results showed model (AUC = 0.832, RMSE 0.144) performed slightly better than 0.814, 0.181) predicting future floods. Further, these demonstrated an improved compared previous studies used same area. network successful capturing heterogeneity patterns Province, resulting can be development plans response general policy implication our suggests design, implementation, verification systems should directed approximately 40% area characterized by high very susceptibility flooding.

Language: Английский

---