Biosensor in Climate Change and Water Rise Analysis Based on Diverse Biological Ecosystems Using Machine Learning Model

The stability of environmental conditions around the world has been threatened by climate change in the last few decades. Sea levels are rising more quickly than ever before due to a combination of factors including temperature increases, changes in precipitation patterns, and glacier melting. We describe a machine learning strategy to design coastal sea level fluctuation as well as related uncertainty across a range of timescales by utilising important ocean temperature estimations as proxies for regional thermosteric sea level component. The aim of this research is to propose novel method in climate change with water level rise analysis using biosensor with machine learning techniques in diverse biological ecosystems. Here, the input is collected as biosensor-based climate analysis with water level rise analysis dataset and processed for noise removal, normalisation, and smoothening. Then, climate data analysis is carried out utilising fuzzy adversarial encoder (FAE) model and the water level rise analysis is carried out using recurrent transfer AlexNet neural network (RTAlexNetNN). The classified output shows climate change analysis with water level rise modelling. The experimental analysis has been carried out for various climate data and water rise data in terms of random accuracy, specificity, MSE, F-measure, and normalised cross-correlation. The proposed technique obtained 98% random accuracy, 96% normalised cross-correlation, 94% specificity, 58% MSE, and 92% F-measure.