Enhancing the strength and toughness of polylactic acid-based composites through one-step co-deposition of active coating onto wood fiber.

A facial strategy of co-deposition is proposed to enhance the interfacial bonding in wood fiber (WF)/polylactic acid (PLA) composites. Dopamine or tannic acid (TA) was co-deposited with 3-aminopropyltriethoxysilane (APTES) onto the WF surface to create active coatings. These coatings were formed through Michael addition and Schiff base reactions and effectively attached to the WF through a combination of hydrogen and covalent bonding. Such active coatings facilitated the connection between WF and PLA through both covalent bonds and physical entanglements, thereby enhancing the interfacial interactions and compatibility between the two components. The co-deposition of TA with APTES was found to be more effective than with dopamine, leading to a dramatic improvement in the tensile strength and elongation at break of the composites by 33.4 % and 185.9 %, respectively. This work offers a facile method to prepare high performance plant fiber reinforced PLA composites, thereby broadening the potential applications of PLA.

Multi-source information fusion-driven corn yield prediction using the Random Forest from the perspective of Agricultural and Forestry Economic Management.

The objective of this study is to promptly and accurately allocate resources, scientifically guide grain distribution, and enhance the precision of crop yield prediction (CYP), particularly for corn, along with ensuring application stability. The digital camera is selected to capture the digital image of a 60 m × 10 m experimental cornfield. Subsequently, the obtained data on corn yield and statistical growth serve as inputs for the multi-source information fusion (MSIF). The study proposes an MSIF-based CYP Random Forest model by amalgamating the fluctuating corn yield dataset. In relation to the spatial variability of the experimental cornfield, the fitting degree and prediction ability of the proposed MSIF-based CYP Random Forest are analyzed, with statistics collected from 1-hectare, 10-hectare, 20-hectare, 30-hectare, and 50-hectare experimental cornfields. Results indicate that the proposed MSIF-based CYP Random Forest model outperforms control models such as support vector machine (SVM) and Long Short-Term Memory (LSTM), achieving the highest prediction accuracy of 89.30%, surpassing SVM and LSTM by approximately 13.44%. Meanwhile, as the experimental field size increases, the proposed model demonstrates higher prediction accuracy, reaching a maximum of 98.71%. This study is anticipated to offer early warnings of potential factors affecting crop yields and to further advocate for the adoption of MSIF-based CYP. These findings hold significant research implications for personnel involved in Agricultural and Forestry Economic Management within the context of developing agricultural economy.