Search

This paper presents a novel deep learning (DL) framework for predicting methane emissions from landfills by analyzing images of solid waste mixtures. The generation of renewable and sustainable electricity from landfills is a rapidly developing field that has gained considerable interest due to its potential to reduce greenhouse gas (GHG) emissions. Methane is a potent GHG produced during the decomposition of solid waste in landfills, significantly contributing to climate change. Precise estimation of methane emissions is crucial for efficient landfill management and the development of mitigation strategies. The framework is composed of four phases. During the initial phase, object detection identifies individual items within the landfill waste images. Subsequently, a hybrid Inception-ResNet-V2 DL method is suggested for categorizing the resulting waste image data into four classes: organic, paper and textile, wood, and food waste. In the next phase, the total weight of waste for each of the four classes is calculated utilizing a suggested method called waste weight estimation (WWE). Following that, methane production is estimated in the third phase using a proposed method (CH4PE), which relies on the weight values of waste mixtures. Finally, the fourth phase entails estimating electricity production using the electricity production estimation (EPE) method, which is based on the obtained methane weight. The validation findings revealed that the classification accuracy attained 93%. Additionally, the framework's findings confirm a total estimated methane weight of 39,695.03kg in the landfill case study, along with an estimated electricity production of 474,449.7kW/month. This framework presents numerous advantages over conventional methods for predicting landfill-based methane emissions. It eliminates the necessity for labour-intensive manual waste classification and offers scalability, enabling application on large-scale landfill sites. This scalability facilitates the identification of high-emission areas and optimization of gas collection systems, fostering green and sustainable electricity production.