Mine ecological restoration is a critical process for promoting the sustainable development of resource-dependent regions, yet existing monitoring methods remain limited in accuracy and adaptability. To address challenges such as small-object recognition, insufficient multi-scale feature fusion, and blurred boundaries in UAV-based remote sensing imagery, this paper proposes an enhanced semantic segmentation model based on Segformer. Specifically, a multi-scale feature-enhanced feature pyramid network (MSFE-FPN) is introduced between the encoder and decoder to strengthen cross-level feature interaction. Additionally, a selective feature aggregation pyramid pooling module (SFA-PPM) is integrated into the deepest feature layer to improve global semantic perception, while an efficient local attention (ELA) module is embedded into lateral connections to enhance sensitivity to edge structures and small-scale targets. A high-resolution UAV image dataset, named the HUNAN Mine UAV Dataset (HNMUD), is constructed to evaluate model performance, and further validation is conducted on the public Aeroscapes dataset. Experimental results demonstrated that the proposed method exhibited strong performance in terms of segmentation accuracy and generalization ability, effectively supporting the image analysis needs of mine restoration scenes.

To enhance the accessibility and accuracy of plant protection knowledge for agricultural practitioners, this study develops an intelligent question-answering (QA) system based on a large language model (LLM). A local knowledge base was constructed by vectorizing 7000 research papers and books in the field of plant protection, from which 568 representative papers were selected to generate QA data using an LLM. After data cleaning and filtering, a fine-tuning dataset comprising 9000 question–answer pairs was curated. To optimize the model’s performance, low-rank adaptation (LoRA) was applied to the InterLM-20B model, resulting in the InterLM-20B-LoRA, which was integrated with Langchain-ChatChat and the local knowledge base to develop the QA system. Additionally, retrieval-augmented generation (RAG) technology was implemented to enhance response accuracy by enabling the model to retrieve relevant field-specific knowledge before generating answers, effectively mitigating the risk of hallucinated information. The experimental results demonstrate that the proposed system achieves an answer accuracy of 97%, highlighting its potential as an advanced solution for intelligent agricultural QA services.

In view of the current problems of complex models and insufficient data processing in ultra-short-term prediction of photovoltaic power generation, this paper proposes a photovoltaic power ultra-short-term prediction model named HPO-KNN-SRU, based on a Simple Recurrent Unit (SRU), K-Nearest Neighbors (KNN), and Hunter–Prey Optimization (HPO). Firstly, the sliding time window is determined by using the autocorrelation function (ACF), partial correlation function (PACF), and model training. The Pearson correlation coefficient method is used to filter the principal meteorological factors that affect photovoltaic power. Then, the K-Nearest Neighbors (KNN) algorithm is utilized for effective outlier detection and processing to ensure the quality of input data for the prediction model, and the Hunter–Prey Optimization (HPO) algorithm is applied to optimize the parameters of the KNN algorithm. Finally, the efficient Simple Recurrent Unit (SRU) model is used for training and prediction, with the Hunter–Prey Optimization (HPO) algorithm applied to optimize the parameters of the SRU model. Simulation experiments and extensive ablation studies using photovoltaic data from the Desert Knowledge Australia Solar Centre (DKASC) in Alice Springs, Australia, validate the effectiveness of the integrated model, the KNN outlier handling, and the HPO algorithm. Compared to the Support Vector Regression (SVR), Long Short-Term Memory (LSTM), Temporal Convolutional Network (TCN), and Simple Recurrent Unit (SRU) models, this model exhibits an average reduction of 19.63% in Mean Square Error (RMSE), 27.54% in Mean Absolute Error (MAE), and an average increase of 1.96% in coefficient of determination ($R^2$) values.

Wheat breeding heavily relies on the observation of various traits during the wheat growth process. Among all traits, wheat head density stands out as a particularly crucial characteristic. Despite the realization of high-throughput phenotypic data collection for wheat, the development of efficient and robust models for extracting traits from raw data remains a significant challenge. Numerous fully supervised target detection algorithms have been employed to address the wheat head detection problem. However, constrained by the exorbitant cost of dataset creation, especially the manual annotation cost, fully supervised target detection algorithms struggle to unleash their full potential. Semi-supervised training methods can leverage unlabeled data to enhance model performance, addressing the issue of insufficient labeled data. This paper introduces a one-stage anchor-based semi-supervised wheat head detector, named “Wheat Teacher”, which combines two semi-supervised methods, pseudo-labeling, and consistency regularization. Furthermore, two novel dynamic threshold components, Pseudo-label Dynamic Allocator and Loss Dynamic Threshold, are designed specifically for wheat head detection scenarios to allocate pseudo-labels and filter losses. We conducted detailed experiments on the largest wheat head public dataset, GWHD2021. Compared with various types of detectors, Wheat Teacher achieved a mAP0.5 of 92.8% with only 20% labeled data. This result surpassed the test outcomes of two fully supervised object detection models trained with 100% labeled data, and the difference with the other two fully supervised models trained with 100% labeled data was within 1%. Moreover, Wheat Teacher exhibits improvements of 2.1%, 3.6%, 5.1%, 37.7%, and 25.8% in mAP0.5 under different labeled data usage ratios of 20%, 10%, 5%, 2%, and 1%, respectively, validating the effectiveness of our semi-supervised approach. These experiments demonstrate the significant potential of Wheat Teacher in wheat head detection.

Existing diffusion models outperform generative models like Generative Adversarial Networks in image synthesis and editing. However, they struggle with high-precision image editing while preserving image details and the accuracy of editing instructions. To address these challenges, we propose a dual attention control method to achieve high-precision image editing. Our approach includes two key attention control modules: (1) cross-attention control module, which combines the cross-attention maps of the original and edited images through weighted parameters, ensures that the synthesized edited image retains the structure of the input image. (2) Self-attention control module, which varies based on the editing task, applied at “coarse” and “fine” layers, since the coarse layers help maintain input image details and the fine layers are better suited for style transformations. Experimental evaluations have demonstrated that our approach achieves excellent results in detail preservation, content consistency, visual realism, and semantic understanding, making it especially suitable for tasks requiring high-precision editing. Specifically, compared to the editing outcomes under no control conditions, the introduction of dual visual attention control has led to an increase of 6.19% in CLIP scores, a reduction of 29.3% in LPIPS, and a decrease of 24.7% in FID. These significant improvements not only validate the effectiveness of the dual attention control but also attest to the method’s substantial flexibility and adaptability across different scenarios. Notably, our approach is a zero-shot solution, requiring no user optimization or fine-tuning, facilitating real-world applications.

Across seven public educational prediction datasets, three passed all four pre-modeling reliability checks; the remaining four either failed group-aware generalization tests or lacked the provenance metadata needed to run them. One dataset was initially classified as failing but corrected after excluding group-identifier features from the holdout matrix, demonstrating that the audit can distinguish genuine cross-group confounding from feature-encoding artifacts. Each dataset was audited before model optimization using four checks: baseline gap, split instability, null separation, and metadata adequacy under group-aware holdout. The dominant failure mode was not weak iid performance alone but cross-group fragility: in the clearest case, UCI Student declined from iid $$R^2 = 0.242$$ to group-holdout $$R^2 = -0.097$$ , while Higher Ed collapsed from 0.041 to $$-8.79$$ . Increasing model complexity did not remove this pattern: ensemble models improved structurally sound datasets but amplified instability or failed under group holdout on fragile ones. An exploratory cross-dataset comparison further showed that stronger profiles clustered in larger, richer-grouped, performance-proximal datasets, while random-split performance severely overstated deployable signal in fragile datasets. Classification-metric sensitivity analyses reached the same substantive conclusions. The results show that benchmark reliability in educational AI is constrained less by algorithm choice than by data structure, group heterogeneity, and evaluation design. A reusable pre-modeling audit offers a minimum quality gate before public educational datasets support strong benchmark or deployment claims.