Oilseed flax (Linum usitatissimum L.) is an important oil crop, and the SIMPLE model is a very effective tool to simulate crop production. In this study, to adapt the SIMPLE model for the overall improvement of flax production and yield, three promising cultivars of North China—Longya Hybrid No. 1, Baxuan No. 3 and Zhangya No. 2—were selected. Experiments were conducted in Dingxi, Wulanchabu, Datong and Zhangjiakou in Northern China from 2016 to 2020. The SIMPLE model was first calibrated and then evaluated for the simulation of flax growth and development and grain yield and biomass. A base temperature of 5 °C was used for phenology, with optimum temperatures from 16 to 20 °C for the third pair of true leaves to unfolded to the budding stage, and from 20 to 25 °C for the flowering stage. In the results, the average simulated value of aboveground biomass in Dingxi was 8772 kg ha⁻¹, with a root mean square error (RMSE) of 1239 kg ha⁻¹ (d-index = 0.69). The simulations were also good in the other three sites according to a comparison of the predicted and observed biomasses (RMSE 135 kg ha⁻¹ and d-index 0.90 at Zhangjiakou, RMSE 280 kg ha⁻¹ and d-index 0.95 at Wulanchabu, and RMSE 140 kg ha⁻¹ and d-index 0.97 at Datong). Flax grain yield was well simulated compared with the observed values, with a RMSE of 55 kg ha⁻¹ and a d-index of 0.96 for Dingxi, a RMSE of 63 kg ha⁻¹ and a d-index of 0.93 for Wulanchabu, and a RMSE of 5 kg ha⁻¹ and a d-index of 0.97 for Zhangjiakou, whereas the yield was somewhat underestimated for Datong (RMSE of 176 kg ha⁻¹ and d-index of 0.91). Overall, the SIMPLE model provided satisfactory predictions under different environments and management. Care should be taken when transferring the SIMPLE-Flax model to other environments, as vernalization and day-length sensitivity are not included in this model.

The impact of climate change on crop production is a major concern in drought-prone regions, which are experiencing increasingly severe drought conditions. The goal of this study was to use the Agricultural Production System Simulator (APSIM) model to simulate and predict flax yield and water balance, as well as to determine the optimal irrigation and fertilizer for flax production to counteract the effects of climate change under arid and semiarid conditions. The model was calibrated using field experimental data from 2019 to 2020 and evaluated using field experimental data from 2021 to 2022 with a combination of four irrigation treatments (full irrigation, 180 mm, deficit irrigation at vegetative and reproductive stage, no irrigation) and four fertilizer rates (no fertilizer, NPK, NPK + flax oil residue, NPK + farm manure) using a plot design for a total of 16 treatments. To determine the key irrigation and fertility periods and irrigation and fertilization amounts that affect flax yield to address climate change, a combination of four irrigation and six fertilizer rates and six irrigation stages were simulated. The results showed that the model successfully predicted flax yield (R² = 0.98) and water-use efficiency (WUE) (R² = 0.79). When compared to inorganic fertilization, the grain yield and WUE improved by 16.47% and 13.83%; replacing 50% of inorganic fertilizer with flax oil residue achieved the optimal results. The flax yield and WUE increased by 3.37% and 1.25% under full irrigation (180 mm) compared to irrigation of 120 mm with a not-very-significant difference. The positive effect of irrigation on soil water content (SWC) was highest during the budding stage, followed by the flowering stage, fruiting stage, and stemming stage. Therefore, in arid and semiarid areas with scarce water resources, irrigation at a 55% deficiency during the vegetative growth period of flax combined with the application of flax oil residue and NPK (1550 flax oil residue, 45 N, 50.2 P₂O₅, and 33.9 K₂O kg ha⁻¹) might be an effective adaptation strategy for improved future flax production. Our results can facilitate the development of sustainable agriculture practices that reduce water input and improve WUE to counteract climate change effects.

In the detection of the pests and diseases of flax, early wilt disease is elusive, yellow leaf disease symptoms are easily confusing, and pest detection is hampered by issues such as diversity in species, difficulty in detection, and technological bottlenecks, posing significant challenges to detection efforts. To address these issues, this paper proposes a flax pest and disease detection method based on an improved YOLOv8n model. To enhance the detection accuracy and generalization capability of the model, this paper first employs the Albumentations library for data augmentation, which strengthens the model’s adaptability to complex environments by enriching the diversity of training samples. Secondly, in terms of model architecture, a Bidirectional Feature Pyramid Network (BiFPN) module is introduced to replace the original feature extraction network. Through bidirectional multi-scale feature fusion, the model’s ability to distinguish pests and diseases with similar features and large scale differences is effectively improved. Meanwhile, the integration of the SimAM attention mechanism enables the model to learn information from three-dimensional channels, enhancing its perception of pest and disease features. Additionally, this paper adopts the EIOU loss function to further optimize the model’s bounding box regression, reducing the distortion of bounding boxes caused by high sample variability. The experimental results demonstrate that the improved model achieves a significant detection performance on the flax pest and disease dataset, with notable improvements in the detection accuracy and mean average precision compared to the original YOLOv8n model. Finally, this paper proposes a YOLOv8n model with a four-headed detection design, which significantly enhances the detection capability for small targets such as pests and diseases with a size of 4 × 4 pixels or larger by introducing new detection heads and optimizing feature extraction. This method not only improves the detection accuracy for flax pests and diseases but also maintains a high computational efficiency, providing effective technical support for the rapid and precise detection of flax pests and diseases and possessing an important practical application value.

Oilseed flax (Linum usitatissimum, L.) is an important specialty oilseed crop cultivated in arid and semi-arid regions, where timely, accurate yield prediction is crucial for regional oilseed security and agricultural decision-making. To address the lack of robust county-level yield prediction models for oilseed flax, this study proposes a CNN–Informer hybrid framework that integrates convolutional neural networks (CNNs) with the Informer architecture to model multi-source spatio-temporal data. Unlike conventional Transformer-based approaches, the proposed framework combines CNN-based local temporal feature extraction with the ProbSparse attention mechanism of Informer, enabling the efficient modeling of long-range temporal dependencies across multiple years while reducing the computational burden of attention-based time-series modeling. The model incorporates multi-source inputs, including remote sensing indices (NDVI, EVI, SAVI, KNDVI), TerraClimate meteorological variables, soil properties, and historical yield records. Comprehensive experiments conducted at the county level in Gansu Province, China, demonstrate that the CNN–Informer model consistently outperforms representative machine learning and deep learning baselines (Transformer, Informer, LSTM, and XGBoost), achieving an average performance of R² = 0.82, RMSE = 0.31 t/ha, MAE = 0.21 t/ha, and MAPE = 10.33%. Results from feature ablation and historical yield window analyses reveal that a three-year historical yield window yields optimal performance, with remote sensing features contributing most strongly to predictive accuracy, while meteorological and soil variables enhance spatial adaptability under heterogeneous environmental conditions. Model robustness was further verified through fivefold county-based spatial cross-validation, indicating stable performance and strong generalization capability in unseen regions. Overall, the proposed CNN–Informer framework provides a reliable and interpretable solution for county-level oilseed flax yield prediction and offers practical insights for precision management of specialty crops in arid and semi-arid regions.

Introduction: Plant diseases pose a significant threat to global food security and agricultural productivity, making accurate and timely disease identification essential for effective crop management and minimizing economic losses. Although data augmentation techniques such as RICAP improve model robustness, their reliance on randomly extracted image regions can introduce label noise, potentially misleading the training of deep learning models.Methods: This study introduces Enhanced-RICAP, an advanced data augmentation technique designed to improve the accuracy of deep learning models for plant disease detection. Enhanced-RICAP replaces random patch selection with an attention module guided by class activation maps, focusing on discriminative regions, Enhanced-RICAP reduces label noise and improves model accuracy for plant disease detection, addressing a key limitation of traditional augmentation methods. The method was evaluated using several deep learning architectures, such as ResNet18, ResNet34, ResNet50, EfficientNet-b, and Xception, on the cassava leaf disease and PlantVillage tomato leaf disease datasets.Results: The experimental results demonstrate that Enhanced-RICAP consistently outperforms existing augmentation methods, including CutMix, MixUp, CutOut, Hide-and-Seek, and RICAP, across key evaluation metrics: accuracy, precision, recall, and F1-score. The ResNet18+Enhanced-RICAP configuration achieved 99.86% accuracy on the tomato leaf disease dataset, whereas the Xception+Enhanced-RICAP model attained 96.64% accuracy in classifying four cassava leaf disease categories.Discussion and Conclusion: To bridge the gap between research and practical application, the ResNet18+Enhanced-RICAP model was deployed in PlantDisease, a mobile application that enables real-time disease identification and management recommendations. This approach supports sustainable agriculture and strengthens food security by providing farmers with accessible and reliable diagnostic tools.

Various crop rotation patterns can result in differences in nutrient consumption and the accumulation of toxic substances in the soil, indirectly impacting the soil environment and its nutrient supply capacity. Implementing optimized crop planting practices is beneficial for maintaining the favorable physical and chemical properties of farmland soil in the arid area of northwestern China. This study aimed to establish a crop rotation pattern to improve key enzyme activities and soil nitrogen conversion efficiency, as well as understand the underlying mechanism for enhancing nitrogen supply capacity. A field experiment was conducted to study the effect of four flax planting patterns, which included 13 crop rotation patterns with different crop frequencies: 100% Flax (Cont F), 50% Flax (I) (WFPF, FPFW, PFWF, FWFP), 50% Flax (II) (FWPF, WPFF, PFFW, FFWP), 25% Flax (WPWF, PWFW, WFWP, FWPW), on the key enzyme activities and the rate of soil nitrogen conversion, as well as the nitrogen supply capacity. Here, F, P, and W represent oilseed flax, potato, and wheat, respectively. The results indicated that the wheat stubble significantly increased the intensity of soil ammonification and denitrification before planting. Additionally, the activity levels of soil nitrate reductase and nitrite reductase under wheat stubble were significantly increased by 66.67% to 104.55%, while soil urease activity significantly decreased by 27.27–133.33% under wheat stubble compared to other stubbles. After harvest, the activities of soil nitrate reductase and nitrite reductase under the wheat stubble decreased significantly, and the intensity of soil ammonification, nitrification, and denitrification reduced significantly by 7.83–27.72%. The WFWP and FWFP treatments led to a significant increase in soil nitrogen fixation intensity under various crop rotations after harvest and significantly increased the levels of inorganic nitrogen in the soil before the planting of the next crop. This study suggests that the long-term rotation planting patterns WFWP and FWFP can significantly enhance the key enzyme activities of soil nitrogen conversion and significantly improve soil nitrogen conversion before crop sowing. This may increase the rate of soil nitrogen transfer and raise the available nitrogen content of the soil. These findings are crucial for reducing soil nitrogen loss and improving soil nitrogen nutrient supply capacity in dry areas of the Loess Plateau of China.