Third Sustainable Development Goal (SDG) aims for healthy lives and promote well-being for all for better readability. Among SDG3, end malaria by 2030 is one such complex task. The present research focuses on the reduction of malaria in the tribal agency of the Visakhapatnam district, called as Integrated Tribal Development Agency Paderu, where Annual Parasite Indices (API) are 3.300816 during 2016–2020. The API of the study area is very high, where limited research measures to address the issue. Present research proposes a novel combination of spatial predictive metric, i.e., Spatial Analysis for Malaria Risk Reduction (SAMRR), which is cost effective and efficient in identifying the Probable Malaria Risk Zone based on the environment and climatic parameters such as Temperature, Rainfall, Normalized Difference Vegetation Index, Water bodies of the study area. The proposed SAMRR predictive performance is good with a higher accuracy of 91.5%, when compared with Max Entropy, Generalized Linear and Bayesian Decision Networks models.

第三个可持续发展目标 (SDG) 旨在促进健康生活并促进所有人的福祉，以提高可读性。在可持续发展目标 3 中，到 2030 年消除疟疾就是一项复杂的任务。目前的研究重点是减少维沙卡帕特南地区部落机构（称为帕德鲁综合部落发展机构）的疟疾，该机构 2016 年至 2020 年的年度寄生虫指数 (API) 为 3.300816。该研究领域的 API 非常高，解决该问题的研究措施有限。目前的研究提出了一种空间预测指标的新颖组合，即减少疟疾风险的空间分析（SAMRR），该方法在根据温度、降雨量、归一化等环境和气候参数识别可能的疟疾风险区方面具有成本效益和效率。研究区植被指数、水体差异。与最大熵、广义线性和贝叶斯决策网络模型相比，所提出的 SAMRR 预测性能良好，准确度高达 91.5%。