Dr. Siddique Akhtar Ehsan is a multidisciplinary researcher whose work spans geophysics, signal processing, materials science, and machine learning. He has extensive experience in digital signal processing, including acquisition, storage, filtering, visualization, and reconstruction of signals, with applications in acoustics and geophysical investigations. His work includes developing algorithms for noise removal, signal extraction, and image generation, enabling accurate interpretation of complex datasets.

Dr. Ehsan is proficient in resistivity data analysis and has applied these skills to delineate karst zones, groundwater reservoirs, and subsurface structures, contributing to environmental, geotechnical, and hazard assessment studies.

In materials science, his research encompasses Energy storage devices and supercapacitors, including 3D flexible electrodes derived from biomass materials, fabricated via electrospinning and in situ polymerization of polyaniline to enhance supercapacitive performance. 2D NbSe2/MoS2 heterostructures, focusing on bandgap engineering and tuning of optoelectronic properties through first-principles calculations. Multiferroic capacitors, where DFT-based studies examine switching energy in single-phase multiferroic materials for low-energy electronic applications.

Since 2023, Dr. Ehsan has focused on machine learning and geospatial modeling, leveraging GIS-integrated computational intelligence techniques to address environmental and hydrological challenges. His recent research includes malaria risk mapping in flood-prone districts using geospatial and machine learning approaches to inform public health decision-making as well as weighted ensemble machine learning for groundwater potential mapping in semi-arid basins, demonstrating predictive capabilities for water resource management in the DG Khan Division, Pakistan. These studies highlight his expertise in combining spatial analysis with advanced machine learning methods to generate actionable insights for environmental and societal applications.

He has published extensively, with his work indexed on Google Scholar and ResearchGate, demonstrating a commitment to integrating computational, experimental, and analytical methods across multiple disciplines to address complex challenges in earth sciences, energy storage, functional materials, and machine learning applications.