D. Nandhini

D. Nandhini

Auto-generated profile, based on publicly available information

D. Nandhini

Department of Ocean Engineering, IIT Madras, Chennai, India

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 May 2024 in Physics of Fluids
Verified
Journal Article
Closed access
PDF file
DND. Nandhini
D. Nandhini
KMK. Murali
K. Murali
HSHarish Selvam
Harish Selvam
Holger SchüttrumpfHolger Schüttrumpf
Holger Schüttrumpf
KHKira Heins
Kira Heins
TGThomas Gries
Thomas Gries
River protection structures, especially spur dikes, play a vital role in the hydrodynamic and morphological changes in a river system. Since the earliest days, numerous studies have been carried out to understand the flow characteristics around spur dikes by varying the spacing between them, the length, the shape, the permeability, and the submergence. Despite several studies, knowledge of flow characteristics around spur dikes is still poorly understood, resulting in damages and failures worldwide. Furthermore, such failures get aggravated under extreme conditions like floods, land-slide-induced surges and tidal bores. Therefore, this state-of-the-art review paper provides a comprehensive account of relevant studies on the flow interaction and its characteristics in the vicinity of spur dikes during normal and extreme scenarios. Possible failure mechanisms with a detailed examination of scour in the proximity of spur dikes are deliberated. Suitable design features and international standards of various types of spur dikes are appraised through this comprehensive review. Furthermore, we also identified a number of research gaps that need immediate attention. This review paper, as a whole, provides concrete knowledge of the flow interaction with spur dikes and design components of spur dikes, thereby helping researchers to understand the advancement in the research area and providing hydraulic engineers with guidance for designing the spur field at a specific site based on the requirements.

3 February 2025 in Ocean Engineering
Verified
Journal Article
Open access
DND. Nandhini
D. Nandhini
Holger SchüttrumpfHolger Schüttrumpf
Holger Schüttrumpf
HSHarish Selvam
Harish Selvam
KMK. Murali
K. Murali

11 December 2025 in Environmental Sciences Europe
Verified
Journal Article
Open access
PDF file
SSShyam Sundhar
Shyam Sundhar
SSS. Shashannk
S. Shashannk
DND. Nandhini
D. Nandhini
ABAmutha Benziker
Amutha Benziker
The world’s median population is projected to reach 8.8 billion by 2050, making water management, especially groundwater, increasingly important. This research article seeks to address the pressing need for an effective method of evaluating and forecasting groundwater quality. Traditionally, water quality testing methods entail significant experimentation, a time-consuming procedure. To overcome this challenge in an alternative way, our proposed methodology involves parameterizing groundwater physicochemical parameters (Q-value) using machine learning algorithms. Focusing on groundwater samples collected from the Russell River of Australia between December 2016 and April 2020 (scaled to approximately 1300 datapoints on average), this research article uses the concept of Q value, a standardized measure facilitating comprehensive water quality assessment. This study significantly contributes to sustainable water resource management by providing a comprehensive examination of groundwater quality through the utilization of deep learning algorithms. The proposed models, namely Conv-LSTM with Attention, Conv-Bi-LSTM with Attention, LSTM with Attention, and Bi-LSTM with Attention, not only offer a distinctive framework for forecasting Q values but also serve as essential tools for timely decision making in water resource distribution. Among these, the Bidirectional LSTM with Attention model achieved the highest predictive accuracy, with a root mean square error of 0.0057, a mean absolute error of 0.0022, a symmetric mean absolute percentage error of 3.8875%, and a coefficient of determination of 0.9910. These results demonstrate its effectiveness in capturing variability and accurately explaining observed trends in groundwater quality. The proposed framework is a reliable, scalable, and timely decision-support tool for water resource management and policy making.

17 October 2025 in Applied Ocean Research
Verified
Journal Article
Open access
DND. Nandhini
D. Nandhini
HSHarish Selvam
Harish Selvam
Holger SchüttrumpfHolger Schüttrumpf
Holger Schüttrumpf
VSV. Sundar
V. Sundar
VSVenkatachalam Sriram
Venkatachalam Sriram

10 June 2026 in Applied Ocean Research
Verified
Journal Article
Open access
DND. Nandhini
D. Nandhini
HSHarish Selvam
Harish Selvam
KMK. Murali
K. Murali
Holger SchüttrumpfHolger Schüttrumpf
Holger Schüttrumpf

31 July 2024 in International Journal on Engineering Artificial Intelligence Management, Decision Support, and Policies
Verified
Journal Article
Open access
PDF file
AAAakash
Aakash
ABAmutha Benziker
Amutha Benziker
DND. Nandhini
D. Nandhini
ANAnsh
Ansh
Tomatoes are regarded as fruits since they fit the botanical definition of a fruit because they are the fleshy parts of a plant that enclose its seeds. There are approximately 10 different kinds of diseases for a tomato plant, which is huge in number and can create huge losses for the farmers. This paper focuses on the classification of tomato plant leaf diseases using Convolution Neural Net-work (CNN) a deep learning technique that is especially employed for image recognition and pixel data processing activities. CNN has been used to identify whether the given photo of the plant is of a healthy or unhealthy part. The secondary dataset that was taken was trained using two algorithms Incep-tion-v3 and VGG19. VGG19 is a 19 layered algorithm, comprising 16 convolu-tional layers and 3 fully linked layers. Inception-v3 is the algorithm is a CNN-based algorithm that has 48 layers in it. The pre-trained networks can categorize photos into several different item categories, including several an-imals, types, diseases and much more. The dataset that is being used to train and validate the model is secondary data taken from Kaggle. The models were trained with 1900 images of healthy tomato plants, and 1800 images of un-healthy tomato plants. The model was also validated with 500 images of healthy and 1080 images of unhealthy tomato plants. The Inception V3 model was able to achieve an accuracy of 98% and a validation accuracy of 89% and VGG19 achieved an accuracy of 94%. Inception-v3 was the chosen model for the paper.