Yuexiang Yuan

This study introduces the Hierarchical Pixel-Wavele ngth Fusion Network (HPWF-Net), a novel hyperspectral reconst ruction framework designed to address the challenges of tree spe cies classification and spectral reconstruction in complex forest ecosystems. The proposed method employs a hierarchical pixel-wise and target-wavelength-wise reconstruction strategy, progressivel y recovering hyperspectral images by dynamically selecting and r efining target wavelengths at each layer. HPWF-Net utilizes an e nhanced U-Net architecture with multi-level loss supervision and convolutional consistency constraints, enabling accurate reconstr uction by supervising intermediate encoder outputs, convolutiona l regressions, and final decoder predictions. This design preserves consistency with the original multispectral input while enhancin g spectral fidelity and robustness. The model is trained on hypers pectral data from the NEON dataset and applied to Sentinel-2 m ultispectral imagery of the Daiyun Mountain National Nature Re serve. Experimental results demonstrate that the reconstructed h yperspectral data improve tree species classification accuracy by 5.9% compared to the original Sentinel-2 multispectral data. This work contributes to hyperspectral reconstruction and fine-grain ed ecological monitoring, offering a practical solution for remote sensing applications in forest ecosystems. Furthermore, we offer a Python-based package that enable to replicate our results at https://github.com/DarkFlameMaster02/Hierarchical-Pixel-Wave length-Fusion-Network-for-Progressive-Hyperspectral-Image-Re construction.

To investigate the effects of organic loading rate (OLR) on performance and stability of mesophilic co-digestion of rice straw (RS) and chicken manure (CM), benchtop experiments (40 L) were carried out at OLRs of 3.0, 3.6, 4.2, 4.8, 6.0, 8.0, and 12.0 kg volatile solid (VS)/(m³·day) with volatile solid (VS) ratio of 1:1 (RS/CM) which was based on batch tests. Anaerobic co-digestion was slightly and severely inhibited by the accumulation of ammonia when the digester was overloaded at an OLR of 6 and 12 kg VS/(m³·day), respectively. The recommended OLR for co-digestion is 4.8 kg VS/(m³·day), which corresponds to average specific biogas production (SBP) of 380 L/kg VS and volumetric biogas production rate (VBPR) of 1.8 m³/(m³·day). An OLR of 6–8 kg VS/(m³·d) with SBP of 360–440 L/kg VS and VBPR of 2.1–3.5 m³/(m³·day) could be considered, if an Anaerobic digestion (AD) system assisted by in situ removal of ammonia was adopted.