EcoDetect-YOLO: A Lightweight, High-Generalization Methodology for Real-Time Detection of Domestic Waste Exposure in Intricate Environmental Landscapes.

In response to the challenges of accurate identification and localization of garbage in intricate urban street environments, this paper proposes EcoDetect-YOLO, a garbage exposure detection algorithm based on the YOLOv5s framework, utilizing an intricate environment waste exposure detection dataset constructed in this study. Initially, a convolutional block attention module (CBAM) is integrated between the second level of the feature pyramid etwork (P2) and the third level of the feature pyramid network (P3) layers to optimize the extraction of relevant garbage features while mitigating background noise. Subsequently, a P2 small-target detection head enhances the model's efficacy in identifying small garbage targets. Lastly, a bidirectional feature pyramid network (BiFPN) is introduced to strengthen the model's capability for deep feature fusion. Experimental results demonstrate EcoDetect-YOLO's adaptability to urban environments and its superior small-target detection capabilities, effectively recognizing nine types of garbage, such as paper and plastic trash. Compared to the baseline YOLOv5s model, EcoDetect-YOLO achieved a 4.7% increase in mAP0.5, reaching 58.1%, with a compact model size of 15.7 MB and an FPS of 39.36. Notably, even in the presence of strong noise, the model maintained a mAP0.5 exceeding 50%, underscoring its robustness. In summary, EcoDetect-YOLO, as proposed in this paper, boasts high precision, efficiency, and compactness, rendering it suitable for deployment on mobile devices for real-time detection and management of urban garbage exposure, thereby advancing urban automation governance and digital economic development.

Empirical assessment of carbon emissions in Guangdong Province within the framework of carbon peaking and carbon neutrality: a lasso-TPE-BP neural network approach.

The escalating global greenhouse gas emission crisis necessitates a robust scientific carbon accounting framework and innovative development approaches. Achieving emission peaks remains the primary goal for emission reduction. Guangdong Province, a pivotal region in China, faces pressure to reduce carbon emissions. In this study, data was leveraged from the China Carbon Accounting Database (CEADS) and panel data from the "Guangdong Statistical Yearbook" spanning 1997 to 2022. Factors impacting carbon emissions were selected based on Guangdong Province's carbon reduction goals, macroeconomic development strategies, and economic-population dynamics. To address multicollinearity, lasso regression identified key factors, including population size, economic development level, energy intensity, and technology factors. A novel STIRPAT extended model, combined with the BP neural network optimized using the TPE algorithm, enhanced carbon emission predictions for Guangdong Province. Employing scenario analysis, five scenarios were generated in alignment with the planning policies of Guangdong Province, to forecast carbon emissions from 2020 to 2050. The results suggest that to achieve a win-win situation for both economic development and environmental protection, Guangdong Province should prioritize the energy-saving scenario (S2), which aligns with the "13th Five-Year Plan's" ecological and green development directives, to reach a projected carbon peak of 637.05Mt by 2030. In conclusion, recommendations for carbon reduction are proposed in the areas of low-carbon transformation for the population, sustainable economic development, and the development of low-carbon technologies.

[Characteristics of Elements and Potential Ecological Risk Assessment of Heavy Metals in PM2.5 at the Southwest Suburb of Chengdu in Spring].

PM2.5 samples were collected at the southwest suburb of Chengdu in spring (in May 2012 and 2014). The mass concentrations of PM2.5 were determined by the weight method, and 24 chemical elements in PM2.5 were analyzed by XRF. To study the pollution characteristics and sources of chemical elements, and the potential ecological risk of heavy metals in PM2.5, the Geo-accumulation Index, Enrichment Factor, and Potential Ecological Risk Index methods were applied, respectively. The results indicated that the mass concentrations of PM2.5 in spring at the southwest suburb of Chengdu were very high, compared with American EPA's Standard and National Standard level-Ⅱ. The detection of chemical element composition in PM2.5 showed that K and S were the main elements, whereas the contents of Ga, Cs, Co, Cd, and V were the lowest. The differences of elemental concentrations in PM2.5 showed relatively large differences, when compared with domestic and foreign representative cities. Se, Cd, As, Br, S, Pb, Cl and Zn were present at an extremely high level of geo-accumulation degree, which revealed that the pollution coming from human activities was serious. The analysis results of enrichment factor showed that Se, Cd, As, Br, Cl, Pb, Zn and S elements were highly enriched or hyper accumulated, Cu, Cs, Ni, Ga and Co elements were moderately enriched, and they were mainly from human activities rather than soil dust. Cr, Mn, Ca and V elements were mildly enriched, and they were from both natural sources and human activities. Na, Ti, Al, Si and Mg elements were scarcely enriched, and they were mainly from natural sources. The ecological risk assessment of heavy metals showed that the order of potential ecological risk inedx of heavy metals in PM2.5 was Cd > As > Pb > Cu > Zn > Ni > Co > Cr > Mn > V > Ti, while the ecological harm degree of Cd was extremely strong, and the whole potential ecological risk degree was very strong.