Crop production is inherently sensitive to variability in climate. Temperature is a major determinant of the rate of plant development and, under climate change, warmer temperatures that shorten development stages of determinate crops will most probably reduce the yield of a given variety. Earlier crop flowering and maturity have been observed and documented in recent decades, and these are often associated with warmer (spring) temperatures. However, farm management practices have also changed and the attribution of observed changes in phenology to climate change per se is difficult. Increases in atmospheric [CO(2)] often advance the time of flowering by a few days, but measurements in FACE (free air CO(2) enrichment) field-based experiments suggest that elevated [CO(2)] has little or no effect on the rate of development other than small advances in development associated with a warmer canopy temperature. The rate of development (inverse of the duration from sowing to flowering) is largely determined by responses to temperature and photoperiod, and the effects of temperature and of photoperiod at optimum and suboptimum temperatures can be quantified and predicted. However, responses to temperature, and more particularly photoperiod, at supraoptimal temperature are not well understood. Analysis of a comprehensive data set of time to tassel initiation in maize (Zea mays) with a wide range of photoperiods above and below the optimum suggests that photoperiod modulates the negative effects of temperature above the optimum. A simulation analysis of the effects of prescribed increases in temperature (0-6 degrees C in +1 degree C steps) and temperature variability (0% and +50%) on days to tassel initiation showed that tassel initiation occurs later, and variability was increased, as the temperature exceeds the optimum in models both with and without photoperiod sensitivity. However, the inclusion of photoperiod sensitivity above the optimum temperature resulted in a higher apparent optimum temperature and less variability in the time of tassel initiation. Given the importance of changes in plant development for crop yield under climate change, the effects of photoperiod and temperature on development rates above the optimum temperature clearly merit further research, and some of the knowledge gaps are identified herein.

Objective To quickly and accurately assess the situation of crop lodging disasters, it is necessary to promptly obtain information such as the location and area of the lodging occurrences. Currently, there are no corresponding technical standards for identifying crop lodging based on UAV remote sensing, which is not conducive to standardizing the process of obtaining UAV data and proposing solutions to problems. This study aims to explore the impact of different spatial resolution remote sensing images and feature optimization methods on the accuracy of identifying wheat lodging areas. Methods Digital orthophoto images (DOM) and digital surface models (DSM) were collected by UAVs with high-resolution sensors at different flight altitudes after wheat lodging. The spatial resolutions of these image data were 1.05, 2.09, and 3.26 cm. A full feature set was constructed by extracting 5 spectral features, 2 height features, 5 vegetation indices, and 40 texture features from the pre-processed data. Then three feature selection methods, ReliefF algorithm, RF-RFE algorithm, and Boruta-Shap algorithm, were used to construct an optimized subset of features at different flight altitudes to select the best feature selection method. The ReliefF algorithm retains features with weights greater than 0.2 by setting a threshold of 0.2; the RF-RFE algorithm quantitatively evaluated the importance of each feature and introduces variables in descending order of importance to determine classification accuracy; the Boruta-Shap algorithm performed feature subset screening on the full feature set and labels a feature as green when its importance score was higher than that of the shaded feature, defining it as an important variable for model construction. Based on the above-mentioned feature subset, an object-oriented classification model on remote sensing images was conducted using eCognition9.0 software. Firstly, after several experiments, the feature parameters for multi-scale segmentation in the object-oriented classification were determined, namely a segmentation scale of 1, a shape factor of 0.1, and a tightness of 0.5. Three object-oriented supervised classification algorithms, support vector machine (SVM), random forest (RF), and K nearest neighbor (KNN), were selected to construct wheat lodging classification models. The Overall classification accuracy and Kappa coefficient were used to evaluate the accuracy of wheat lodging identification. By constructing a wheat lodging classification model, the appropriate classification strategy was clarified and a technical path for lodging classification was established. This technical path can be used for wheat lodging monitoring, providing a scientific basis for agricultural production and improving agricultural production efficiency. Results and Discussions The results showed that increasing the altitude of the UAV to 90 m significantly improved flight efficiency of wheat lodging areas. In comparison to flying at 30 m for the same monitoring range, data acquisition time was reduced to approximately 1/6th, and the number of photos needed decreased from 62 to 6. In terms of classification accuracy, the overall classification effect of SVM is better than that of RF and KNN. Additionally, when the image spatial resolution varied from 1.05 to 3.26 cm, the full feature set and all three optimized feature subsets had the highest classification accuracy at a resolution of 1.05 cm, which was better than at resolutions of 2.09 and 3.26 cm. As the image spatial resolution decreased, the overall classification effect gradually deteriorated and the positioning accuracy decreased, resulting in poor spatial consistency of the classification results. Further research has found that the Boruta-Shap feature selection method can reduce data dimensionality and improve computational speed while maintaining high classification accuracy. Among the three tested spatial resolution conditions (1.05, 2.09, and 3.26 cm), the combination of SVM and Boruta-Shap algorithms demonstrated the highest overall classification accuracy. Specifically, the accuracy rates were 95.6%, 94.6%, and 93.9% for the respective spatial resolutions. These results highlighted the superior performance of this combination in accurately classifying the data and adapt to changes in spatial resolution. When the image resolution was 3.26 cm, the overall classification accuracy decreased by 1.81% and 0.75% compared to 1.05 and 2.09 cm; when the image resolution was 2.09 cm, the overall classification accuracy decreased by 1.06% compared to 1.05 cm, showing a relatively small difference in classification accuracy under different flight altitudes. The overall classification accuracy at an altitude of 90 m reached 95.6%, with Kappa coefficient of 0.914, meeting the requirements for classification accuracy. Conclusions The study shows that the object-oriented SVM classifier and the Boruta-Shap feature optimization algorithm have strong application extension advantages in identifying lodging areas in remote sensing images at multiple flight altitudes. These methods can achieve high-precision crop lodging area identification and reduce the influence of image spatial resolution on model stability. This helps to increase flight altitude, expand the monitoring range, improve UAV operation efficiency, and reduce flight costs. In practical applications, it is possible to strike a balance between classification accuracy and efficiency based on specific requirements and the actual scenario, thus providing guidance and support for the development of strategies for acquiring crop lodging information and evaluating wheat disasters.

为及时准确地获取干旱区农作物种植信息，研究借助PIE-Engine Studio平台，以新疆焉耆盆地为研究区，基于2022年Sentinel-2影像和1948个野外定位采样数据提取农作物生育期内14种植被指数，使用See5.0决策树、随机森林（Random forest，RF）和多元回归（Multiple regression，MR）模型优选特征参数，结合支持向量机（Support vector machine，SVM）算法构建5种分类模型和5种样方分割方案进行农作物种植信息提取，通过目视解译和混淆矩阵对比分析分类结果，确定最佳分类方案。结果表明：（1） 所有分类模型的总体精度（OA）和Kappa系数均在92.20%和0.9037以上，说明在PIE平台中使用SVM算法提取农作物信息是可行的。（2） SVM-有红边的OA和Kappa系数均值为93.77%和0.9236，比SVM-无红边方法提高了0.96%和0.0120。（3） 相比于SVM-有红边方法，植被指数的引入提高了SVM-RF、SVM-MR和SVM-See5.0的OA和Kappa系数。（4） 5种分类模型的OA和Kappa系数均值的大小关系为：SVM-RF>SVM-MR>SVM-See5.0>SVM-有红边>SVM-无红边，表明红边波段和植被指数的加入显著提高了农作物识别的精度，其中SVM-RF（8:2）为最佳分类模型，OA和Kappa系数分别为98.72%和0.9866。研究结果可为准确快速获取大尺度干旱区农作物信息提供新的思路和参考依据。

To obtain timely and accurate information about crop cultivation in arid zones, this study used the PIE-Engine Studio platform to extract 14 vegetation indices in the Yanqi Basin, Xinjiang, China based on 2022 Sentinel-2 images and 1948 field location sampling data during the crop reproduction period. Crop planting information was extracted using the See5.0 decision tree, random forest (RF), and multiple regression (MR) models to select feature parameters. Each model was combined with support vector machine (SVM) algorithms to construct five classification models and five sample segmentation schemes. The best classification scheme was determined by visual interpretation and confusion matrix comparison. The results are as follows: (1) The overall accuracy (OA) and Kappa coefficients of all classification models are above 92.20% and 0.9037, respectively, indicating that it is feasible to extract crop information using the SVM algorithm in the PIE platform. (2) The mean OA and Kappa coefficients of SVM-with-red-edge are 93.77% and 0.9236, which are 0.96% and 0.0120, respectively. (3) The introduction of vegetation index improved the OA and Kappa coefficients of SVM-RF, SVM-MR, and SVM-See5.0 compared with the SVM-with-red-edge method. (4) The mean OA and Kappa coefficient relationships for the five classification models were SVM-RF>SVM-MR>SVM-See5.0>SVM-with-red-edge>SVM-without-red-edge, showing that the inclusion of the red-edge band and vegetation index significantly improved the accuracy of crop identification, with SVM-RF (8:2) being the best classification model with OA and Kappa coefficients of 98.72% and 0.9866, respectively. These results provide new ideas and references for accurate and rapid access to large-scale arid zone crop information.

Through the observation and research of whole phenological stage of summer maize in agrometeorological station in Hebi city, Henan province and by means of field monitoring image capture device to collect different maize image data and analyzing image feature of group images as well as parameters with a variety of colors, the identification of the main phenological stage can be attained. For different phenological stage, RGB color space to extract green pixel value and HSL color space to extract yellow pixel value are used to determine the proportion of developmental period. For the weed effect on the extraction image color, proposed using small area elimination algorithm based on region labeling to eliminate weed impact in pictures. For wet soil on the extraction of the interference of the yellow pixel value in pictures, proposed combining S value of HSL color space to eliminate the color of wet soil. After comparison with the manual observation, the results showed that it is available to identify maize developmental period by using color parameters. The correct recognition rate reaches 94.26%.