Mingfang He

Potato leaf diseases seriously affect potato yield and quality. Accurate recognition and localization of visible lesions associated with potato early blight and late blight can support preliminary disease screening and targeted field inspection. Object detection can identify disease categories and locate lesion regions, providing reliable information for disease management. However, potato leaf diseases usually occur in complex field environments, where illumination changes, shadows, color shifts, leaf texture interference, and imaging blur may weaken lesion feature representation. In addition, early blight and late blight lesions often have small scales, weak boundaries, irregular shapes, and scattered distributions, making detection prone to background misclassification, missed small lesions, and localization deviation. To address these problems, this study proposes TRP-Net, a text-guided dual-modal detection network, for the robust recognition and localization of visible lesions associated with potato early blight and late blight under complex imaging conditions. First, a Text-Anchored Counterfactual Intervention Module (TACIM) is proposed to construct environmentally perturbed images and constrain feature consistency, improving the robustness of disease representations. Second, a Residual Cross-Modal Attention module (RCMA) is introduced to guide visual features with textual semantics and enhance lesion boundaries and fine-grained textures. Third, a P4 Gaussian Position Distribution Auxiliary Loss (PGDAL) is designed to provide position distribution supervision during early training, improving small-lesion localization. Experimental results on the independent test set show that TRP-Net achieves 78.3% Precision, 73.7% Recall, 75.9% F1 score, 80.5% mAP50, and 34.6% mAP50–95. The detector-side network contains 2.79 M parameters and requires 5.2 GFLOPs. The performance gap between mAP50 and mAP50–95 indicates that precise lesion localization under stricter IoU criteria remains challenging.

Plantations play an essential role in regional ecological security and the sustainable use of forest resources, making accurate knowledge of their spatial distribution and management boundaries critical for forest inventories, afforestation assessment, carbon-accounting support, and stand-level management. To address blurred stand boundaries, complex background interference, and regional spectral variation, we propose a plantation segmentation framework termed the Kernel-Guided Forest Segmentation Network (KGF-Net). The method combines a spectral-index aligned fusion module (SIAF), a structure-aware boundary enhancement module (SABE), a cross-domain discriminative geometry-constrained coupling module (CDGC), and an Adam-compatible forest-aware responsive spectral control strategy (FReSCO). In the source-domain stage, KGF-Net is pretrained on the North American subset using aligned RGB, NDVI, and EVI inputs, enabling the model to learn vegetation-sensitive spectral and structural representations. For Asia, Europe, Africa, and public FAIS target datasets, no target-domain vegetation-index layers are used; instead, the source-domain weights are transferred and the model is fine-tuned separately using target-domain RGB images and plantation masks. Thus, the cross-region experiments evaluate source-to-target transfer learning with RGB-based target adaptation rather than zero-shot generalization or independent multimodal training in every region. Experiments show that KGF-Net achieves competitive segmentation and boundary-delineation performance while maintaining a compact computational profile. The resulting maps provide spatially explicit information on plantation extent, patch configuration, and management boundaries, supporting regional plantation monitoring and forest-management applications.

Stone cells are an important structural component of rubber tree bark and are closely associated with traits such as cracking propensity, bark hardness, stress tolerance and latex production. However, high-precision segmentation methods that are robust to staining variations, morphological diversity, and scale changes are still missing. To address these challenges in stone-cell histological images, such as the inconsistent staining intensity, the diverse shapes and sizes of cells, and the interference of cell debris, we proposed an automated semantic segmentation network called FLDO-LKNet, which formulates stone-cell delineation as a pixel-wise semantic segmentation task. Specifically, we introduce an LDFE module to recalibrate backbone features at the channel level, thereby mitigating the effects of staining differences. A KCFA attention mechanism is designed to better capture complex morphology and scale variation. In addition, we develop an FLDO optimization algorithm with a performance-feedback-based dynamic learning rate adjustment strategy to enhance robustness against training instability caused by debris interference. We further construct a dataset of 1084 stone-cell images collected from CATAS to support model training and evaluation. Experimental results demonstrate that FLDO-LKNet achieves 75.18% mIoU, 98.5% accuracy, and 82.21% sensitivity. Overall, as a dedicated semantic segmentation network, the proposed method enables high-precision pixel-level segmentation of stone cells, which may facilitate subsequent studies of stone-cell development and genetic functions and shows potential for agricultural applications.

Accurate carbon price for ecasting is crucial for the management of emission trading schemes and the formulation of low-carbon policies. However, existing models face three intertwined challenges: the interdependent multi-agent strategies among market participants, the long-term time dependence of high-dimensional environmental and economic covariates, and the severe nonlinearity under the constraint of small samples. This paper proposes the novel hybrid framework EvoGame-CAKNet. Firstly, an evolutionary game theory (EGT) is proposed to simulate the evolution of dynamic strategies of different market participants (enterprises, regulatory agencies, financial institutions), and policy effect signals are embedded as structured prior information. Secondly, a knowledge network (CAKNet) combining multi-head context attention is designed for adaptive long-distance feature aggregation across climate, macroeconomy, and policy dimensions. Finally, a Kolmogorov–Arnold network (KAN) is proposed to replace the traditional multi-layer perceptron decoder, using learnable unary activation functions to achieve better nonlinear fitting under data scarcity conditions. Experiments on four major carbon markets in Beijing, Shanghai, Hubei, and Guangdong from 2014 to 2023 show that EvoGame-CAKNet achieves the most advanced performance, with an average absolute percentage error (MAPE) reduced by 18.3% to 31.6% compared to the best base model. Abandonment studies confirm that each component works collaboratively, with the prior knowledge of EGT having the most significant impact during the regulatory transition period. CAKNet not only provides theoretical progress in multi-agent market modeling but also offers practical decision support for stakeholders in the carbon market.

With the rapid development of UAV and satellite remote sensing, in combination with deep learning, high-efficiency monitoring of pine wilt disease (PWD) for forest health management is now feasible. Accurate detection has not yet been realised. The sensing platforms have different ranges of space, observation areas and imaging orientations. At the same time, the target groups for PWD often have weak phenotypic features, are easily affected by a complex forest background, and show irregular data distributions at different stages of the disease. The above factors are limits to the performance of traditional methods based only on general visual features. To address the problems mentioned above, we propose the cross-platform semantic-consistent and phenotype-adaptive detection network SCPA-Net for high-precision PWD detection in both UAV and satellite images. First, we construct a cross-platform multimodal framework to integrate remote sensing images and disease-related text descriptions. The above design adds semantic prior knowledge to expand the model’s capacity for high-level phenotypic attribute extraction without direct observation. Second, to reduce the semantic gap caused by the different platforms, improve the semantic consistency of UAV and satellite images, strengthen discriminative feature channels and salient regions, and address cross-platform misalignment. Third, since the targets are often associated with complex forest environments, target-context relational modeling is enhanced and irrelevant interference is suppressed to reduce the impact of non-causal attributes. As pine wilt disease symptoms gradually progress from mild to severe (e.g., crown discoloration, texture variation, and wilting severity), differences among disease stages may lead to learning imbalance and knowledge forgetting; therefore, a staged adaptation strategy has been proposed. First, the model learns from relatively easy examples. Subsequently, it progressively learns from more difficult examples to enhance generalization performance. Experiments have been conducted on a self-built cross-platform dataset, a satellite dataset, the PDT public dataset, and the Roboflow dataset, and the proposed method has achieved better detection accuracy and generalization. The framework can address the problem of PWD detection in challenging-to-process forestry remote sensing data reasonably well.

With the rapid development of unmanned aerial vehicle (UAV) remote sensing and deep learning technologies, the efficient monitoring of pine wood nematode disease (Pine Wilt Disease, PWD) has become increasingly important. However, the repetitive tree crown textures, strong random noise, and complex background in high-altitude UAV images make it difficult for traditional methods relying solely on visible light data to stably identify diseased trees. To address this issue, this paper proposes TVIM (Text-Enhanced UAV Framework with Vegetation-Index Masking) for accurately locating PWD targets in high-altitude images. Firstly, we, with the participation of forestry experts, constructed the first high-altitude UAV PWD multimodal annotated dataset. Then, we integrated text priors into visual features through the Epidemic Semantics-Augmented Detection Module (ESADM) to enhance the model’s semantic understanding ability. Secondly, we proposed VI-based Threshold Mask Filtering (VTMF), which enhances the spectral differences of diseased trees and suppresses illumination and terrain noise based on green light enhancement and normalization strategies. Thirdly, we designed the Multi-Resolution Adaptive KAN Module (MRA-KAN), which adaptively suppresses random noise while retaining key high-frequency texture details. Subsequently, we introduced the Quad-Region Diffusion Graph Convolutional Residual Attention Block (Q-DGCRAB), which achieves the synergy of frequency domain enhancement and spatial relationship modeling based on regional division and graph structure modeling. Finally, we developed the Forest Guardian Algorithm with Collaborative Evolution (FGA-CE), which improves training stability and multi-scale adaptability through multi-population parallel search and dynamic parameter adjustment. Experimental results show that TVIM achieves excellent performance on the self-built dataset, the PDT public dataset, and the Roboflow public dataset. This framework provides an efficient and stable technical solution for the precise location of PWD in high-altitude UAV environments.

The stock market is of paramount importance to economic development. Investors who accurately predict stock price fluctuations based on its high volatility can effectively mitigate investment risks and achieve higher returns. Traditional time series models face limitations when dealing with long sequences and short-term volatility issues, often yielding unsatisfactory predictive outcomes. This paper proposes a novel algorithm, MSNet, which integrates a Multi-scale Channel Attention mechanism (MSCA) and Sparse Perturbation Greedy Optimization (SPGO) onto an xLSTM framework. The MSCA enhances the model’s spatio-temporal information modeling capabilities, effectively preserving key price features within stock data. Meanwhile, SPGO improves the exploration of optimal solutions during training, thereby strengthening the model’s generalization stability against short-term market fluctuations. Experimental results demonstrate that MSNet achieves an MSE of 0.0093 and an MAE of 0.0152 on our proprietary dataset. This approach effectively extracts temporal features from complex stock market data, providing empirical insights and guidance for time series forecasting.