Earth System Sciences: Integrating Remote Sensing and Hybrid Deep Learning to Develop a Legal Framework for Surrogacy Rights

Surrogacy, as an alternative reproductive technology, has garnered widespread attention due to its intricate legal, ethical, and health-related intricacies. The escalation of surrogacy agreements, particularly transnationally, highlights the need for stringent oversight to ensure that practices adhere to legal norms and safeguard all involved parties. This paper integrates earth system sciences and introduces a cutting-edge hybrid deep learning model that combines EfficientNet and support vector machine (SVM) for the analysis and monitoring of surrogacy practices using remote sensing imagery and legal document scrutiny. Employing advanced image processing and natural language processing (NLP) techniques, the model extracts significant features from varied data sets, classifying them to assess adherence to surrogacy regulations. Through meticulous data preprocessing, the model’s accuracy is significantly enhanced, achieving a remarkable 96.88% in detecting compliance and pinpointing legal and health discrepancies at surrogacy centres. This method provides a scalable and robust solution for regulatory authorities and stakeholders, promoting compliance and upholding ethical standards in global surrogacy practices.