Machine learning-driven prediction of phosphorus removal performance of metal-modified biochar and optimization of preparation processes considering water quality management objectives.

Developing an optimized and targeted design approach for metal-modified biochar based on water quality conditions and management is achievable through machine learning. This study leveraged machine learning to analyze experimental data on phosphate adsorption by metal-modified biochar from literature published in Web of Science. Using six machine learning models, the phosphate adsorption capacity of biochar and residual phosphate concentration were predicted. After hyperparameter optimization, the gradient boosting model exhibited superior training performance (R2 > 0.96). Metal load quantity, solid-liquid ratio, and pH were key factors influencing adsorption performance. Optimal preparation parameters indicated that Mg-modified biochar achieved the highest adsorption capacity (387-396 mg/g), while La-modified biochar displayed the lowest residual phosphate concentration (0 mg/L). The results of verification experiments based on optimized process parameters closely aligned with model predictions. This study introduces a new machine learning-based approach for tailoring biochar preparation processes considering different water quality management objectives.

VMF-SSD: A Novel V-Space Based Multi-Scale Feature Fusion SSD for Apple Leaf Disease Detection.

Apple leaf diseases seriously affect the quality of apples and may lead to yield losses, detecting apple leaf diseases accurately can prevent diseases from spreading and promote the healthy growth of the industry. However, recent studies cannot achieve accurate detection of leaf diseases with high accuracy because the lesions are of different sizes. So, this paper proposed a novel apple leaf disease detection method called VMF-SSD (V-space-based Multi-scale Feature-fusion SSD), which is designed to extract more reliable multi-scale feature representations for varied sizes of diseased spots and improve the final detection performance. The multi-scale feature extraction is established with multi-scale feature representation to further improve the disease detection performance, especially for small spots. After that, a V-space-based location branch is presented to enhance the texture feature information and help further identify disease spot location. Finally, attention mechanisms are utilized to automatically learn the importance of feature channels at different scales for distinguishing diseased spots of different sizes. Experimental results showed that the VMF-SSD method achieves 83.19% mAP and obtains the detection speed of 27.53 FPS on the test set, which indicates that the proposed VMF-SSD method can achieve competitive performance on apple leaf diseases detection task and satisfy the requirements of agricultural production applications.

LAD-Net: A Novel Light Weight Model for Early Apple Leaf Pests and Diseases Classification.

Aphids, brown spots, mosaics, rusts, powdery mildew and Alternaria blotches are common types of early apple leaf pests and diseases that severely affect the yield and quality of apples. Recently, deep learning has been regarded as the best classification model for apple leaf pests and diseases. However, these models with large parameters have difficulty providing an accurate and fast diagnosis of apple leaf pests and diseases on mobile terminals. This paper proposes a novel and real-time early apple leaf disease recognition model. AD Convolution is firstly utilized to replace standard convolution to make smaller number of parameters and calculations. Meanwhile, a LAD-Inception is built to enhance the ability of extracting multiscale features of different sizes of disease spots. Finally, the LAD-Net model is built by the LR-CBAM and the LAD-Inception modules, replacing a full connection with global average pooling to further reduce parameters. The results show that the LAD-Net, with a size of only 1.25MB, can achieve a recognition performance of 98.58%. Additionally, it is only delayed by 15.2ms on HUAWEI P40 and by 100.1ms on Jetson Nano, illustrating that the LAD-Net can accurately recognize early apple leaf pests and diseases on mobile devices in real-time, providing portable technical support.

Dynamic mechanisms for pre-miRNA binding and export by Exportin-5.

The biogenesis and function of mature microRNAs (miRNAs) is dependent on the nuclear export of miRNA precursors (pre-miRNA) by Exportin-5 (Exp5). To characterize the molecular mechanisms of how pre-miRNA is recognized and transported by Exp5, we have performed 21 molecular dynamic (MD) simulations of RNA-bound Exp5 (Exp5-RanGTP-premiRNA, Exp5-RanGDP-premiRNA, Exp5-premiRNA), RNA-unbound Exp5 (Exp5-RanGTP, Exp5-RanGDP, apo-Exp5), and pre-miRNA. Our simulations with standard MD, steered molecular dynamics (SMD), and energy analysis have shown that (1) Free Exp5 undergoes extensive opening motion, and in this way facilitates the RanGTP binding. (2) RanGTP efficiently regulates the association/dissociation of pre-miRNA to its complex by inducing conformational changes in the HEAT-repeat helix stacking of Exp5. (3) The GTP hydrolysis prevents Ran from rebinding to Exp5 by regulating the hydrophobic interfaces and salt bridges between Ran and Exp5. (4) The transition from the A'-form to the A-form of the pre-miRNA modulates the structural complementarities between the protein and the pre-miRNA, thus promoting efficient assembly of the complex. (5) The base-flipping process (from the closed to the fully flipped state) of the 2-nt 3' overhang is a prerequisite for the pre-miRNA recognition by Exp5, which occurs in a sequence-independent manner as evidenced by the fact that different 2-nt 3' overhangs bind to Exp5 in essentially the same way. And finally, a plausible mechanism of the pre-miRNA export cycle has been proposed explaining how the protein-protein and protein-RNA interactions are coordinated in physiological conditions.