Research articles

• Nitu Kumari & Anurag Singh. "Data-driven enhancement of the Hastings–Powell model using sparse identification algorithm." Journal of Computational Science (2025): 102682. https://doi.org/10.1016/j.jocs.2025.102682

• Anurag Singh & Nitu Kumari. Modeling Moose–Wolf interactions in Isle Royale National Park using sparse identification of nonlinear dynamics. Scientific Reports 15, 34683 (2025). https://doi.org/10.1038/s41598-025-08874-7

• Anurag Singh, Nitu Kumari & Arun Kumar. The first Mathematical Model for Elk-Wolf Interaction in Yellowstone National Park using E-SINDy algorithm. Ecological Modelling, 2025. (Submitted)  https://doi.org/10.48550/arXiv.2511.07575 

• Currently working on an inverse problem with the help of Physics-Informed Neural Networks (PINNs).

Projects

• "Cable exposure: detecting when power cables are exposed to the open sea." sponsored by Ørsted, a renewable energy company ( joint work with Abdeltif Oujbara, Joseph, Reza Babaei, and Ramin Jalilian).

In an industry project with Ørsted, developed data-driven methods to detect subsea power cable exposure using temperature and electrical load data.

Compared multiple models, including Dynamic Time Warping, Isolation Forest, CNNs, and PINNs, to identify anomalies. Implemented a Physics-Informed Neural Network (PINN) to solve the inverse problem, estimating key physical parameters of the cable system from sensor data to create a digital twin.