The agricultural sector stands as the cornerstone of a nation's innovative growth, playing a pivotal role in providing sustenance and raw materials. The critical importance of agriculture as a primary food source underscores the pressing need for effective plant disease identification. Traditional methods, reliant on subjective visual inspection by agriculture professionals or plant pathologists, have proven to be time-intensive and resource-demanding. So, this study introduces a technologically advanced solution by harnessing the capabilities of Machine Learning (ML) and Deep Learning (DL) for comprehensive plant disease detection and classification. The research leverages an experimentally evaluated software solution to address the limitations of conventional approaches. The proposed model integrates a sophisticated convolutional neural network (CNN) based on residual networks, facilitating robust feature extraction for accurate disease classification. Additionally, the study incorporates a preprocessing step to eliminate various types of noise with generic algorithm dependent Particle swarm optimization (GA-PSO) feature analysis, thereby enhancing the normalization of dataset images and improving the overall efficacy of the model. Building upon the success of the GA-PSO optimized Residual Network based CNN model in plant disease detection, this study extends its scope to include a novel aspect – pesticide suggestion, which is named GPR-CNN. The integration of pesticide recommendation systems into the framework aims to provide a holistic solution for managing identified plant diseases. Leveraging the same DL architecture, the model utilizes its learned features to suggest targeted pesticide interventions based on the specific disease detected. The simulation results underscore the efficacy of the proposed GPR-CNN model in not only achieving commendable accuracy rates in plant leaf disease detection and classification but also in offering precise and tailored pesticide suggestions. This innovative approach holds significant promise for revolutionizing agricultural practices, managing, and treating plant diseases. The seamless integration of plant disease detection and pesticide suggestion in a unified framework represents a significant step towards sustainable and technologically driven agriculture