Indian Journal of Geo-Marine Sciences (IJMS)

First record of Blackfin stonefish Pseudosynanceia melanostigma, Day, 1875 (Synanceiidae: Scorpaeniformes) from India

S C Saren — 2025-10-21

The present study documents the first confirmed occurrence of the blackfin stonefish (Pseudosynanceia melanostigma, Day, 1875) from the Indian waters, based on the specimens collected from the coastal regions of Gujarat along the west coast of India. This species, belonging to the family Synanceiidae, was identified through detailed morphological analysis. The key diagnostic features observed include a distinctive colour pattern, bran-chiostegal membranes broadly fused to the isthmus, the specific count of dorsal fin spines, segmented pelvic fin rays, the presence of a large black spot on the anterior part of soft dorsal fins, and two broad dark bars on the caudal fin. Given the limited taxonomic and ecological information available on stone fishes in India, this finding highlights the need for more systematic studies to better understand the distribution, diversity and potential risk associated with venomous marine fishes in the region.

Rare occurrence of Brassy chub, Kyphosus vaigiensis (Quoy & Gaimard, 1825) (Family: Kyphosidae) from Ratnagiri, west coast of India

M B Shetkar — 2025-10-21

The Brassy chub, Kyphosus vaigiensis (Quoy & Gaimard, 1825) is reported for the first time from the Ratnagiri coast along the central part of the Arabian Sea, based on a single specimen collected from Mirkarwada fishing harbour (Ratnagiri, Maharashtra, India). The morphology of the caught specimen, as well as its chromatic and meristic characteristics, confirms that it represents K. vaigiensis.

Unmanned surface vessels in hydrographic surveying: Exploring technological progressions and development challenges

M A Norazaruddin — 2025-10-21

This paper investigates the role of Uncrewed Surface Vessels (USVs) in hydrographic surveying, with a focus on synthesising recent advancements, evaluating operational efficiencies, and addressing challenges in their adoption. A novel aspect of this study is the systematic analysis of specific USVs, providing a comprehensive overview of their deployment in diverse hydrographic applications. By integrating insights from recent developments, the paper explores how USVs leverage technologies such as multibeam sonar, autonomous navigation systems, and artificial intelligence to enhance data accuracy, safety, and accessibility in remote or hazardous marine environments. The paper also highlights challenges, including regulatory gaps, autonomy standardisation, and environmental concerns, and proposes actionable strategies to mitigate these barriers. This review not only provides a detailed synthesis of current capabilities and limitations but also outlines future research directions to advance the integration of USVs into mainstream hydrographic practices. By offering a unique combination of case-specific analysis and broader thematic insights, this paper contributes to the growing body of knowledge on the transformative potential of USVs in maritime surveying.

Convolutional neural network modelling and image analysis techniques for the detection of fish diseases

A A AlZubi — 2025-10-21

Fish rearing or pisciculture holds the key to food security and economic well-being for several countries across the globe. Diseases in fish are the biggest threat due to their rapid spread rate and high calamity, leading to a sharp decrease in fish yield. Deep learning techniques such as Convoluted Neural Networks (CNNs) hold an extremely promising impact on disease detection and raising the predictability of production amount. In this paper, the sequential CNN model indicates rigour and high reliability. The experimental setup consists of a model based on TensorFlow, Keras and 8-core TPU to accelerate computational Machine Learning (ML) tasks. The dataset obtained from Kaggle consists of 457 files depicting seven distinct classes (one healthy and six diseased classes), including all major fish diseases. Image data preprocessing is done by resizing and rescaling to train the optimised model. Image augmentation is done to expand the available data set and resolve overfitting issues within the CNN model. Modelling involves multiclass classification with a convolutional layer to extract features, keeping non-linearity in the model by an activation function. By transfer learning, inadequacies of the dataset are minimised. The proposed CNN model architecture efficaciously classifies various fish diseases. Identification and categorisation are done using Python, and the algorithm’s learning efficiency is predicted to be quite high. The model makes reasonably accurate predictions with an accuracy close to 91 %. A good pattern of learning during the training of the model is observed. These observations indicate the model's remarkable capacity to correctly identify the diseases.

First report of Cistopus platinoidus Sreeja, Norman & Biju Kumar, 2015 (Cephalopoda, Octopoda, Octopodidae) from the tropical Hooghly-Matlah estuary, West Bengal, India

D Bhakta — 2025-10-21

Cistopus platinoidus Sreeja, Norman & Biju Kumar, 2015 is a tropical benthic cephalopod in the Octopodidae family with eight tiny mucous pouches that are present between the bases of each arm. The current findings revealed the presence of the ‘pouched octopus’, C. platinoidus, from the Hooghly-Matlah estuary, West Bengal, India. The mean salinity of the collection sites was measured at 27.80±2.55 ppt, and the location is approx. 75 km from the river mouth and is bordered by mangrove forest. The present study confirms the range extension of C. platinoidus from the west coast (Kerala and Gujarat) to the east coast (West Bengal).