Agravat Pooja, Baldaniya Ajay, Banerjee Biplab, Mohanta Agradeep, Raval Jatin, Mankodi Pradeep
Division of Marine and Freshwater Biology, Department of Zoology, Faculty of Science, The Maharaja Sayajirao University of Baroda, Vadodara, Gujarat, India.
Department of Geography, Faculty of Science, The Maharaja Sayajirao University of Baroda, Vadodara, Gujarat, India.
Environ Sci Pollut Res Int. 2025 Jan 28. doi: 10.1007/s11356-025-35959-7.
This study delves into the Molluscan diversity along the Gujarat coast, India, focusing on the distribution and habitat suitability of four key species: Cerithium caeruleum, Lunella coronata, Peronia verruculata, and Trochus radiatus. Utilizing species distribution models (SDMs) integrated with machine learning algorithms, we assessed the impact of environmental variables on the distribution patterns of these molluscs. Our findings reveal a nuanced understanding of habitat preferences, highlighting the critical roles of salinity, chlorophyll concentration, and water temperature. The MaxEnt model, with the highest area under the curve (AUC) value of 0.63, demonstrated moderate discrimination capability, suggesting room for enhancement in capturing complex ecological interactions. The spatial distribution analysis indicated a random arrangement of species, with no significant spatial autocorrelation observed. This research underscores the significance of advanced modelling techniques in predicting molluscan distributions, providing insights crucial for the conservation and sustainable management of marine biodiversity along the Gujarat coast. The study examined the distribution and habitat suitability of four key molluscan species-C. caeruleum, L. coronata, P. verruculata, and T. radiatus-along the Gujarat coast, India. By integrating SDMs with machine learning algorithms, we assessed how environmental variables such as salinity, chlorophyll concentration, and water temperature influence their distribution patterns. The MaxEnt model was employed, achieving an AUC value of 0.63, indicating moderate discrimination capability and suggesting potential areas for model refinement to better capture complex ecological interactions. Our analysis revealed no significant spatial autocorrelation, suggesting a random spatial distribution of these species. The results highlight the importance of using advanced modeling techniques to predict the distribution of molluscs, which is essential for the conservation and sustainable management of marine biodiversity along the Gujarat coast.
本研究深入探讨了印度古吉拉特邦海岸的软体动物多样性，重点关注四种关键物种的分布和栖息地适宜性，这四种物种分别是蓝口蟹守螺、冠螺、疣荔枝螺和辐射钟螺。利用与机器学习算法相结合的物种分布模型（SDM），我们评估了环境变量对这些软体动物分布模式的影响。我们的研究结果揭示了对栖息地偏好的细致理解，突出了盐度、叶绿素浓度和水温的关键作用。最大熵模型的曲线下面积（AUC）值最高为0.63，显示出中等的判别能力，这表明在捕捉复杂的生态相互作用方面仍有改进空间。空间分布分析表明物种呈随机排列，未观察到显著的空间自相关性。这项研究强调了先进建模技术在预测软体动物分布方面的重要性，为古吉拉特邦海岸海洋生物多样性的保护和可持续管理提供了至关重要的见解。该研究考察了印度古吉拉特邦海岸四种关键软体动物物种——蓝口蟹守螺、冠螺、疣荔枝螺和辐射钟螺的分布和栖息地适宜性。通过将物种分布模型与机器学习算法相结合，我们评估了盐度、叶绿素浓度和水温等环境变量如何影响它们的分布模式。采用了最大熵模型，其AUC值为0.63，表明具有中等判别能力，并暗示了模型改进的潜在领域，以便更好地捕捉复杂的生态相互作用。我们的分析显示没有显著的空间自相关性，这表明这些物种的空间分布是随机的。结果突出了使用先进建模技术预测软体动物分布的重要性，这对于古吉拉特邦海岸海洋生物多样性的保护和可持续管理至关重要。
