Sourabh Garg
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Sourabh Garg has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Baburao Gaddala
Guru Ghasidas Vishwavidyalaya, India
1 shared publication - Bhoopathy Varadharajan
Malla Reddy College of Engineering, India
1 shared publication Hari Krishan Malhotra
Manav Rachna International Institute of Research and Studies, India
1 shared publicationNibedita Das
Tecnia Institute of Advanced Studies, India
1 shared publication- Pravat Jena
Department of Computer Science and Engineering Shiksha 'O' Anusandhan University Bhubaneswar India
1 shared publication - Sarita Azad
School of Mathematical and Statistical Sciences, Indian Institute of Technology Mandi, Himachal Pradesh, India
1 shared publication
Latest Publications
- 13 March 2026
- Published by IGI Global Scientific Publishing
- p. 129-162
AI-Driven Solutions for Monitoring and Managing Groundwater Pollution
Ecosystems, human health, and long-term sustainability are all badly threatened by polluted groundwater. ML and AI offer promising new approaches to this critical problem. In order to effectively monitor, anticipate, and manage groundwater contamination, this chapter investigates the use of AI and ML. Among the main uses discussed are decision-support frameworks for policy-making and resource allocation, predictive modeling for the spread of contaminants, and real-time monitoring of water quality. This chapter delves into the topic of how to enhance data collecting and get valuable insights by combining AI-driven solutions with IoT devices. Additionally, we delve into topics like data scarcity, model reliability, and the ethical implications of AI applications. Through analysis of past and future cases, this chapter demonstrates how AI and ML have the ability to revolutionize methods for controlling groundwater pollution and fostering sustainable management of water resources.
- 13 March 2026
- Published by IGI Global Scientific Publishing
- p. 129-162
AI-Driven Solutions for Monitoring and Managing Groundwater Pollution
Ecosystems, human health, and long-term sustainability are all badly threatened by polluted groundwater. ML and AI offer promising new approaches to this critical problem. In order to effectively monitor, anticipate, and manage groundwater contamination, this chapter investigates the use of AI and ML. Among the main uses discussed are decision-support frameworks for policy-making and resource allocation, predictive modeling for the spread of contaminants, and real-time monitoring of water quality. This chapter delves into the topic of how to enhance data collecting and get valuable insights by combining AI-driven solutions with IoT devices. Additionally, we delve into topics like data scarcity, model reliability, and the ethical implications of AI applications. Through analysis of past and future cases, this chapter demonstrates how AI and ML have the ability to revolutionize methods for controlling groundwater pollution and fostering sustainable management of water resources.
- 8 March 2023
- Published by Wiley in International Journal of Climatology
- Vol. 43 (8) , 3730-3748
Performance evaluation of high‐resolution IMDAA and IMERG for detecting cloudburst events over the Northwest Himalayas
The main goal of this research is to assess the Indian Monsoon Data Assimilation and Analysis (IMDAA), a recently established high‐resolution (0.12° × 0.12°) reanalysis dataset, for observing cloudburst events over the Northwest Himalaya (NWH). In addition, a high‐resolution (0.1° × 0.1°) satellite estimate, the Integrated Multi‐satellitE Retrievals for Global Precipitation Measurement (GPM) version 6 (IMERG‐V06B) (Final run), is validated against the IMDAA. The following is a summary of our significant findings. (1) Reanalysis data from the IMDAA detects 11 out of 16 cloudburst incidences. In addition, 10 events captured in the IMERG‐V06B data are a subset of those captured by IMDAA. According to contingency measures, the probability of detection (POD) of IMERG‐V06B at 99.99th percentile is 33.33%–63.39% along the geographical extent of NWH. When utilizing the improved probability of detection (IPOD) to account for time, the possibility of IMERG‐V06B detecting cloudburst occurrences ranges from 41.24% to 68.25%. (2) According to the finding, the IMDAA accurately detects cloudburst events in Jammu and Kashmir (J&K), where data from the India Metrological Department (IMD) at a resolution of 0.25° × 0.25° have underperformed. As a result, we can deduce that IMDAA can be used to observe extreme events in the Himalayas. IMERG‐V06B is also relevant satellite data for monitoring cloudburst events and validating climate models.
- 8 March 2023
- Published by Wiley in International Journal of Climatology
- Vol. 43 (8) , 3730-3748
Performance evaluation of high‐resolution IMDAA and IMERG for detecting cloudburst events over the Northwest Himalayas
The main goal of this research is to assess the Indian Monsoon Data Assimilation and Analysis (IMDAA), a recently established high‐resolution (0.12° × 0.12°) reanalysis dataset, for observing cloudburst events over the Northwest Himalaya (NWH). In addition, a high‐resolution (0.1° × 0.1°) satellite estimate, the Integrated Multi‐satellitE Retrievals for Global Precipitation Measurement (GPM) version 6 (IMERG‐V06B) (Final run), is validated against the IMDAA. The following is a summary of our significant findings. (1) Reanalysis data from the IMDAA detects 11 out of 16 cloudburst incidences. In addition, 10 events captured in the IMERG‐V06B data are a subset of those captured by IMDAA. According to contingency measures, the probability of detection (POD) of IMERG‐V06B at 99.99th percentile is 33.33%–63.39% along the geographical extent of NWH. When utilizing the improved probability of detection (IPOD) to account for time, the possibility of IMERG‐V06B detecting cloudburst occurrences ranges from 41.24% to 68.25%. (2) According to the finding, the IMDAA accurately detects cloudburst events in Jammu and Kashmir (J&K), where data from the India Metrological Department (IMD) at a resolution of 0.25° × 0.25° have underperformed. As a result, we can deduce that IMDAA can be used to observe extreme events in the Himalayas. IMERG‐V06B is also relevant satellite data for monitoring cloudburst events and validating climate models.