Spectral imaging technique has been widely applied in plant phenotype analysis to improve plant trait selection and genetic advantages. The latest developments and applications of various optical imaging techniques in plant phenotypes were reviewed, and their advantages and applicability were compared. X-ray computed tomography (X-ray CT) and light detection and ranging (LiDAR) are more suitable for the three-dimensional reconstruction of plant surfaces, tissues, and organs. Chlorophyll fluorescence imaging (ChlF) and thermal imaging (TI) can be used to measure the physiological phenotype characteristics of plants. Specific symptoms caused by nutrient deficiency can be detected by hyperspectral and multispectral imaging, LiDAR, and ChlF. Future plant phenotype research based on spectral imaging can be more closely integrated with plant physiological processes. It can more effectively support the research in related disciplines, such as metabolomics and genomics, and focus on micro-scale activities, such as oxygen transport and intercellular chlorophyll transmission.

Accurate maturity recognition of Pleurotus citrinopileatus fruiting bodies is important for growth monitoring and harvest assistance in controlled cultivation. However, multiple developmental stages often coexist within one image, and near-mature fruiting bodies share visual characteristics with both adjacent stages. We developed a two-stage RGB-based framework for instance-level maturity recognition in complex cultivation scenes. After fruiting-body localization, each detected instance was represented by paired local and context views and classified using a DINOv3 ViT-S/16-based ordinal model. The task-specific methodological contribution is a morphology-guided fusion module that incorporates automatically extracted geometric, color, intensity, and edge descriptors into the dual-view visual representation. Object-level matching was used to quantify how detection and classification errors affected the complete pipeline, and temperature scaling was applied for probability calibration. Among five candidate detectors, RF-DETR-Small achieved validation mAP50 and mAP50–95 values of 0.9747 and 0.8813, respectively. On the independent ROI test set, the final classifier achieved an accuracy of 0.8779, a macro F1 of 0.7950, a near-mature F1 of 0.5546, and a QWK of 0.9068. Temperature scaling reduced ECE from 0.1094 to 0.0564 without changing the predicted labels. On 370 original cultivation images containing 475 ground-truth instances, the unfiltered pipeline achieved an object-level macro F1 of 0.7072 and a near-mature F1 of 0.4672. Candidate-box filtering increased these scores to 0.7305 and 0.4885, respectively, but increased the number of missed instances from 14 to 23. These results demonstrate the feasibility of non-destructive instance-level maturity monitoring while identifying near-mature discrimination and candidate-box control as priorities for practical application.

Measuring prices in agricultural e-commerce markets is complicated by promotional spikes, rapid product turnover, and specification heterogeneity. The aim of this study is to develop and validate a reproducible framework that couples promotion-robust weekly price measurement with calibrated short-term forecasting for agricultural e-commerce input markets. Drawing on 452,489 de-identified raw transaction records (448,308 retained after quality control) of tomato, pepper, and lettuce seeds from major Chinese e-commerce platforms (July 2020–October 2025), we construct a weekly Paasche-robust price index with a Top-10 SKU basket and winsorized prices, benchmarked against Laspeyres, Fisher, Törnqvist, and GEKS-TPD formulations. A time-dummy hedonic regression is applied for quality adjustment. Short-term forecasts are generated by a two-level ensemble combining SARIMAX, Temporal Fusion Transformer, and LightGBM via inverse-MAPE weighting, with adaptive conformal intervals for uncertainty quantification. The Paasche-robust index attenuates promotional noise while co-moving closely with superlative formulas (MA-12 correlations > 0.80). Machine-learning models reduce the one-week-ahead MAPE by 42–58% relative to SARIMAX, and the weighted ensemble achieves the best four-week-ahead accuracy for two of three crops. Conformal intervals deliver near-nominal coverage at short horizons. The framework offers a reproducible, deployable tool for real-time monitoring of agricultural e-commerce input markets and supports evidence-based decisions by farmers and policymakers.

Harvest-window recognition of facility-grown Pleurotus ostreatus is challenged by clustered fruiting bodies, occlusion, and subtle differences between near-mature and mature stages. We developed a two-stage framework combining YOLO26s detection with a lightweight dual-view classifier, RepViT-RSG-BEHarvestNet. YOLO26s was selected from four candidate detectors using the validation subset of a 2946-image dataset. Matched detections produced 3547 paired target and context regions of interest. The classifier combined stage-guided expert routing with boundary soft labels and teacher distillation. On the independent test set, YOLO26s achieved a Precision of 0.9681, Recall of 0.9117, and mAP50 of 0.9787. Across ten paired runs on matched test regions, the final classifier achieved a Macro F1 of 0.8827 ± 0.0044, compared with 0.8589 ± 0.0054 for the dual-view baseline, while adding 0.071 M parameters. On the near-mature–mature subset, Macro F1 increased from 0.7994 ± 0.0115 to 0.8563 ± 0.0105. On all 296 test images containing 404 annotated targets, the complete pipeline achieved target-level Precision of 0.7770, Recall of 0.7941, a false harvest rate of 0.1007, and a missed harvest rate of 0.2059. Mean end-to-end latency was 94.7 ms per image. The results show improved boundary classification while identifying detection errors as a remaining constraint on complete-image harvest decisions.

Due to the reliance of deep learning on high-quality datasets and the uncertainty regarding the reproductive period segmentation and image annotation of the Pleurotus citrinopileatus maturity dataset, this study aims to enhance the accuracy of dataset annotation by leveraging the color change patterns of Pleurotus citrinopileatus. First, reproductive period division and color feature analysis were conducted. Specifically, considering the influence of the cultivation environment, a Pleurotus citrinopileatus color feature database was constructed using data from different environmental batches. Second, the growth process of Pleurotus citrinopileatus fruiting bodies was divided into four stages: primordium stage, young mushroom stage, forming stage, and maturation stage. Third, color pattern verification revealed that through HSV color space analysis, the main hue exhibited periodic changes. Experimental data showed that when the main hue exceeded 28°, it entered the next growth stage, decreasing to 23° before rising again, which validated the division of the four reproductive periods from primordium to maturity. Next, feature extraction and model construction were performed. Statistical measures such as mean, variance, and peak values of the H, S, and V channels for each sample were calculated to build a Gradient Boosting Tree (GBT) classification model based on color features. A new dataset was generated by adjusting expert annotations based on model validation. Finally, the experimental results of dataset quality were annotated and performance improvements were verified. Using the YOLO12 model for image feature learning of Pleurotus citrinopileatus, training and testing were conducted with both the original and improved datasets. The improved dataset(0.935 mAP@0.5 vs. 0.91 mAP@0.5), representing a 2.5 percentage point increase. On a test set of 417 images, the accuracy of the improved dataset reached 94.5%, compared to 92% for the original dataset, marking a 2.5 percentage point improvement. In conclusion, analyzing the color features of Pleurotus citrinopileatus effectively guides the division of maturity datasets, thereby enhancing the performance of deep learning-based Pleurotus citrinopileatus maturity recognition models.

Information asymmetry constrains agricultural credit, but repayment and default labels are often unavailable for empirical analysis. Using administrative records for 2970 agricultural enterprises and cooperatives in Beijing linked to bank-authorized credit, this study examines whether multi-source subsidy profiles are associated with observed lending decisions. Two-stage gradient-boosted-tree models compare eight raw administrative features, an externally supplied composite score, and their combination; Shapley Additive exPlanations (SHAP) provides conditional model attributions. No positive authorized credit was observed for economic or share cooperatives. Among the remaining entity types, the combined model predicted accurate positive authorized credit, with an area under the receiver operating characteristic curve (ROC-AUC) of 0.97. Raw administrative features alone had little out-of-fold value for conditional authorized-credit amounts, whereas including the supplied score improved prediction. The framework supports transparent analysis of observed lending where repayment and application process data are unavailable.