With the continuous development of deep learning technology, object detection has received extensive attention across various computer fields as a fundamental task of computational vision. Effective detection of objects in remote sensing images is a key challenge, owing to their small size and low resolution. In this study, a remote sensing image detection (RSI-YOLO) approach based on the YOLOv5 target detection algorithm is proposed, which has been proven to be one of the most representative and effective algorithms for this task. The channel attention and spatial attention mechanisms are used to strengthen the features fused by the neural network. The multi-scale feature fusion structure of the original network based on a PANet structure is improved to a weighted bidirectional feature pyramid structure to achieve more efficient and richer feature fusion. In addition, a small object detection layer is added, and the loss function is modified to optimise the network model. The experimental results from four remote sensing image datasets, such as DOTA and NWPU-VHR 10, indicate that RSI-YOLO outperforms the original YOLO in terms of detection performance. The proposed RSI-YOLO algorithm demonstrated superior detection performance compared to other classical object detection algorithms, thus validating the effectiveness of the improvements introduced into the YOLOv5 algorithm.

Combining biomass, a clean and renewable energy source, with waste plastic, which serves as a good auxiliary fuel, can produce high-quality clean fuel. The performance of biomass-derived fuel can be improved by torrefaction. This study optimized the co-torrefaction of fungus bran and polypropylene (PP) waste plastic to obtain clean solid biofuel with high calorific value and low ash content (AC) using response surface methodology. Two sets of mixed biochars were investigated using a multiobjective optimization method: mass yield–higher heating value–ash content (MY-HHV-AC) and energy yield–ash content (EY-AC). PP increased the heat value, decreased AC, and acted as a binder. The optimal operating conditions regarding reaction temperature, reaction time, and PP blending ratio were 230.68 °C, 30 min, and 20%, respectively, for the MY-HHV-AC set and 220 °C, 30 min, 20%, respectively, for the EY-AC set. The MY-HHV-AC set had properties close to those of peat and lignite. Furthermore, compared with that of the pure biochar, the AC of the two sets decreased by 15.71% and 14.88%, respectively, indicating that the prepared mixed biochars served as ideal biofuels. Finally, a circular economy framework for biobriquette fuel was proposed and prospects for preparing pellets provided.

The pretreatment for torrefaction impacts the performance of biomass fuels and operational costs. Given their diversity, it is crucial to determine the optimal torrefaction conditions for different types of biomass. In this study, three typical solid biofuels, corn stover (CS), agaric fungus bran (AFB), and spent coffee grounds (SCGs), were prepared using fluidized bed torrefaction. The thermal stability of different fuels was extensively discussed and a novel comprehensive fuel index, “displacement level”, was analyzed. The functional groups, pore structures, and microstructural differences between the three raw materials and the optimally torrefied biochar were thoroughly characterized. Finally, the biomass fuel consumption for household heating and water supply was calculated. The results showed that the optimal torrefaction temperatures for CS, AFB, and SCGs were 240, 280, and 280 °C, respectively, with comprehensive quality rankings of the optimal torrefied biochar of AFB (260) > SCG (252) > CS (248). Additionally, the economic costs of the optimally torrefied biochar were reduced by 7.03–19.32%. The results indicated that the displacement level is an index universally applicable to the preparation of solid fuels through biomass torrefaction. AFB is the most suitable solid fuel to be upgraded through torrefaction and has the potential to replace coal.

Food waste can be converted into porous carbon materials with high porosity and abundant functional groups through carbonization and modification, demonstrating promising application prospects in supercapacitors.