A5032447523- Arsenic contamination and mitigation
- Heavy metals in environment
- Landslides and related hazards
- Flood Risk Assessment and Management
- Heavy Metal Exposure and Toxicity
- Water Quality and Pollution Assessment
- Tree Root and Stability Studies
- Fire effects on ecosystems
- Groundwater and Watershed Analysis
- Soil and Unsaturated Flow
- Soil Geostatistics and Mapping
- Geotechnical Engineering and Soil Mechanics
- Grouting, Rheology, and Soil Mechanics
- Soil and Land Suitability Analysis
- Cryospheric studies and observations
- Social and Economic Development in India
- Environmental Justice and Health Disparities
- Coagulation and Flocculation Studies
- Environmental and Agricultural Sciences
- Heavy Metals in Plants
- Gaussian Processes and Bayesian Inference
- Insurance and Financial Risk Management
- Urban and Rural Development Challenges
- Spatial and Panel Data Analysis
- Mining and Resource Management
University of Allahabad
2024
Centre for Artificial Intelligence and Robotics
2021-2024
Sri Ramachandra Institute of Higher Education and Research
2024
Montclair State University
2014-2022
Virtua Health
2019
Patna University
2019
Magadh University
2012
University of California, Berkeley
1996
Shallow landslides damage buildings and other infrastructure, disrupt agriculture practices, can cause social upheaval loss of life. As a result, many scientists study the phenomenon, some them have focused on producing landslide susceptibility maps that be used by land-use managers to reduce injury damage. This paper contributes this effort comparing power effectiveness five machine learning, benchmark algorithms—Logistic Model Tree, Logistic Regression, Naïve Bayes Artificial Neural...
Landslides have multidimensional effects on the socioeconomic as well environmental conditions of impacted areas. The aim this study is spatial prediction landslide using hybrid machine learning models including bagging (BA), random subspace (RS) and rotation forest (RF) with alternating decision tree (ADTree) base classifier in northern part Pithoragarh district, Uttarakhand, Himalaya, India. To construct database, ten conditioning factors a total 103 locations ratio 70/30 were used....
In the present study, Rotation Forest ensemble was integrated with different base classifiers to develop hybrid models namely based Support Vector Machines (RFSVM), Artificial Neural Networks (RFANN), Decision Trees (RFDT), and Naïve Bayes (RFNB) for landslide susceptibility modelling. The validity of these evaluated using statistical methods such as Root Mean Square Error (RMSE), Kappa index, accuracy, area under success rate predictive curves (AUC). Part prone Pithoragarh district,...
Local scour depth at complex piers (LSCP) cause expensive costs when constructing bridges. In this study, a hybrid artificial intelligence approach of random subspace (RS) meta classifier, based on the reduced error pruning tree (REPTree) base namely RS-REPTree, was proposed to predict LSCP. A total 122 laboratory datasets were used and portioned into training (70%: 85 cases) validation (30%: 37 for modeling processes, respectively. The statistical metrics such as mean absolute (MAE), root...
In this study, we have developed five spatially explicit ensemble predictive machine learning models for the landslide susceptibility mapping of Van Chan district Yen Bai Province, Vietnam. model studies, Random Subspace (RSS) was used as learner with Best First Decision Tree (BFT), Functional (FT), J48 (J48DT), Naïve Bayes (NBT) and Reduced Error Pruning Trees (REPT) base classifiers. Data 167 past present landslides various conditioning factors were generation datasets. The results showed...
Landslide is a natural hazard which causes huge loss of properties and human life in many places the world. Mapping landslide susceptibility an important task for preventing combating landslides problems. Main objective this study to use different artificial intelligence methods namely support vector machines (SVM), neural networks (ANN), logistic regression (LR), reduced error-pruning tree (REPT) development models mapping Muong Lay district Vietnam. In total data 217 locations area was...
This paper aims to apply and compare the performance of three machine learning algorithms–support vector (SVM), bayesian logistic regression (BLR), alternating decision tree (ADTree)–to map landslide susceptibility along mountainous road Salavat Abad saddle, Kurdistan province, Iran. We identified 66 shallow locations, based on field surveys, by recording locations landslides a global position System (GPS), Google Earth imagery black-and-white aerial photographs (scale 1: 20,000) 19...
ABSTRACT Health risk assessment due to groundwater As contamination was conducted in two As-prone panchayats, Rampur Diara (RD) and Haldichapra (HC) of the Maner block Patna district, Bihar (India). All 100% water samples surveyed were found be contaminated with a mean value 52 μg/L (n = 10) RD 231 HC, both exceeding World Organization (WHO) guideline 10 Bureau Indian Standards (BIS) standard 50 μg/L, respectively. The average calculated per capita consumption through drinking ranged from...
This study evaluates state-of-the-art machine learning models in predicting the most sustainable arsenic mitigation preference. A Gaussian distribution-based Naïve Bayes (NB) classifier scored highest Area Under Curve (AUC) of Receiver Operating Characteristic curve (0.82), followed by Nu Support Vector Classification (0.80), and K-Neighbors (0.79). Ensemble classifiers higher than 70% AUC, with Random Forest being top performer (0.77), Decision Tree model ranked fourth an AUC 0.77. The...
This opinion article explores the evolving responsibilities of data scientists in current data-driven landscape, which ethical, privacy, and governance standards have grown considerably importance. Although job scientist initially attracted attention for its allure high earning potential, recent years, it has become associated with a particularly level responsibility, requiring practitioners to balance their technical skills commitment social impact accountability. examines essential...
The purpose of this study is to develop a landslide susceptibility prediction model by applying the Frequency Ratio (FR) and remote sensing data sets for Northern part Uttarakhand, India. First, inventory was carried out from interpretation satellite images. Thereafter, points were randomly separated into training validation datasets. Subsequently, significant causative factors such as slope, lithology, lineament density, land use/land cover, drainage aspect, elevation, road buffer,...
Landslides can be a major challenge in mountainous areas that are influenced by climate and landscape changes. In this study, we propose hybrid machine learning model based on rotation forest (RoF) meta classifier random (RF) decision tree called RoFRF for landslide prediction area near Kamyaran city, Kurdistan Province, Iran. We used 118 locations 25 conditioning factors from which their predictive usefulness was measured using the chi-square technique 10-fold cross-validation analysis....
Arsenic is a category-I carcinogen that naturally occurs in the earth's crust and found more than 200 minerals.1 At certain pH, redox, temperature conditions coupled with solution composi...