Penerapan Jaringan Saraf Tiruan untuk Mengelolah Data Perubahan Cuaca sebagai Dasar Prediksi Kondisi Iklim

This study aims to analyze the application of Deep Neural Networks (DNN) as an artificial intelligence approach in processing weather data to support more accurate and stable climate predictions. Increasingly unpredictable and fluctuating weather patterns demand modern analytical methods capable of capturing non-linear relationships among atmospheric variables. DNN is utilized due to its ability to learn complex data structures through multilayer representations that extract deeper features from input variables. Weather data such as temperature, humidity, rainfall, air pressure, and wind speed are processed through several preprocessing stages to ensure optimal model performance. This research employs a descriptive qualitative method based on literature studies to examine the role of DNN in weather prediction systems. The findings indicate that DNN demonstrates strong generalization abilities, robustness to fluctuating data, and more stable predictive outputs compared to conventional statistical approaches. Thus, DNN is considered a promising component for the development of early warning systems and modern data-driven climate analysis, offering improved reliability in understanding and forecasting atmospheric conditions.