Film-stalk spaced dual mulching is a new type of cultivation measure that is increasingly highlighted in semi-arid areas in China.Despite its potential,there is limited understanding of how different mulching material...Film-stalk spaced dual mulching is a new type of cultivation measure that is increasingly highlighted in semi-arid areas in China.Despite its potential,there is limited understanding of how different mulching materials affect both soil quality and crop yield in these areas.To address this gap,we conducted a two-year(2020-2021)field experiment in central China to explore the yield-enhancing mechanisms and assess the impact of various mulching materials on soil and corn yield.The experiment comprised six treatments,i.e.,plastic film-whole stalk spaced mulching in fall(PSF),plastic film-whole stalk spaced mulching in spring(PSS),black and silver plastic film-whole stalk spaced mulching in spring(BPSS),biodegradable film-whole stalk spaced mulching in spring(BSS),liquid film-whole stalk spaced mulching in spring(LSS),and non-mulching cultivation(CK).Results revealed that BPSS demonstrated the most significant yield increase,surpassing CK by a notable 10.0%and other mulching treatments by 2.4%-5.9%.The efficacy of BPSS lied in its provision of favorable hydrothermal conditions for corn cultivation,particularly during hot season.Its cooling effect facilitated the establishment of optimal temperature conditions relative to transparent mulching,leading to higher root growth indices(e.g.,length and surface area),as well as higher leaf photosynthetic rate and dry matter accumulation per plant.Additionally,BPSS maintained higher average soil moisture content within 0-100 cm depth compared with biodegradable mulching and liquid mulching.As a result,BPSS increased activities of urease,catalase,and alkaline phosphatase,as well as the diversity and abundance of soil bacteria and fungi in the rhizosphere zone of corn,facilitating nutrient accessibility by the plant.These findings suggest that selecting appropriate mulching materials is crucial for optimizing corn production in drought-prone areas,highlighting the potential of BPSS cultivation.展开更多
密集场景下群株生菜的有效分割与参数获取是植物工厂生长监测中的关键环节。针对群株生菜中个体生菜鲜质量提取问题,该研究提出一种利用实例分割模型提取个体生菜点云,再以深度学习点云算法预测个体鲜质量的方法。该方法以群株生菜为研...密集场景下群株生菜的有效分割与参数获取是植物工厂生长监测中的关键环节。针对群株生菜中个体生菜鲜质量提取问题,该研究提出一种利用实例分割模型提取个体生菜点云,再以深度学习点云算法预测个体鲜质量的方法。该方法以群株生菜为研究对象,利用深度相机采集群株生菜俯视点云,将预处理后的点云数据输入实例分割模型Mask3D中训练,实现背景与生菜个体的实例分割,之后使用鲜质量预测网络预测个体生菜鲜质量。试验结果表明,该模型实现了个体生菜点云的分割提取,无多检和漏检的情况。当交并比(intersection over union,IoU)阈值为0.75时,群株生菜点云实例分割的精确度为0.924,高于其他实例分割模型;鲜质量预测网络实现了直接通过深度学习处理点云数据,预测个体生菜鲜质量的目的,预测结果的决定系数R2值为0.90,均方根误差值为12.42 g,优于从点云中提取特征量,再回归预测鲜质量的传统方法。研究结果表明该研究预测生菜鲜质量的精度较高,为利用俯视单面点云提取群株生菜中个体生菜表型参数提供了一种思路。展开更多
基金financially supported by the Projects of National Key Research and Development Program of China(2021YFD1901101-5)the Special Major Research and Development Project of Shanxi Province(202101140601026-5)the Earmarked Fund for Modern Agro-industry Technology Research System(2023CYJSTX01-11).
文摘Film-stalk spaced dual mulching is a new type of cultivation measure that is increasingly highlighted in semi-arid areas in China.Despite its potential,there is limited understanding of how different mulching materials affect both soil quality and crop yield in these areas.To address this gap,we conducted a two-year(2020-2021)field experiment in central China to explore the yield-enhancing mechanisms and assess the impact of various mulching materials on soil and corn yield.The experiment comprised six treatments,i.e.,plastic film-whole stalk spaced mulching in fall(PSF),plastic film-whole stalk spaced mulching in spring(PSS),black and silver plastic film-whole stalk spaced mulching in spring(BPSS),biodegradable film-whole stalk spaced mulching in spring(BSS),liquid film-whole stalk spaced mulching in spring(LSS),and non-mulching cultivation(CK).Results revealed that BPSS demonstrated the most significant yield increase,surpassing CK by a notable 10.0%and other mulching treatments by 2.4%-5.9%.The efficacy of BPSS lied in its provision of favorable hydrothermal conditions for corn cultivation,particularly during hot season.Its cooling effect facilitated the establishment of optimal temperature conditions relative to transparent mulching,leading to higher root growth indices(e.g.,length and surface area),as well as higher leaf photosynthetic rate and dry matter accumulation per plant.Additionally,BPSS maintained higher average soil moisture content within 0-100 cm depth compared with biodegradable mulching and liquid mulching.As a result,BPSS increased activities of urease,catalase,and alkaline phosphatase,as well as the diversity and abundance of soil bacteria and fungi in the rhizosphere zone of corn,facilitating nutrient accessibility by the plant.These findings suggest that selecting appropriate mulching materials is crucial for optimizing corn production in drought-prone areas,highlighting the potential of BPSS cultivation.
文摘滑坡地质灾害易发性评价是防灾减灾的一种重要手段,易发性评价模型的选取和优化至关重要。以思南县为研究区,选取高程、坡度、曲率、地层、土地利用、年平均降雨量等16个评价因子,采用频率比(frequency ratio,FR)模型与支持向量机(support vector machine,SVM)模型和随机森林(random forest,RF)模型相耦合,引入网格搜索方法来获取SVM模型、RF模型及其耦合模型最优参数组合并用于模型训练,最终构建SVM、RF、FR-SVM及FR-RF模型对整个研究区进行滑坡易发性预测,并进行了受试者操作特征(receiver operating characteristics,ROC)曲线验证。结果表明:与单一机器学习模型相比,耦合机器学习有更多的滑坡灾害样本落于高易发区和极高易发区,有更高的准确率。单一模型中,RF模型有较多的滑坡灾害样本落于高易发区和极高易发区,耦合模型中,FR-RF模型有较多的滑坡灾害样本落于高易发区和极高易发区,且FR模型和FR-RF模型中没有滑坡灾害样本落在极低易发区,表明无论是单一模型还是耦合模型,RF模型的性能优于SVM模型。4种模型的ROC预测曲线的曲线下面积(area under the curve,AUC)分别为0.8316、0.8439、0.8644、0.9104,说明FR模型与RF模型结合的耦合模型有更高的准确率,该模型更适用于思南县的滑坡易发性评价研究,评价结果可为当地滑坡地质灾害的防灾减灾提供一定的参考。
文摘密集场景下群株生菜的有效分割与参数获取是植物工厂生长监测中的关键环节。针对群株生菜中个体生菜鲜质量提取问题,该研究提出一种利用实例分割模型提取个体生菜点云,再以深度学习点云算法预测个体鲜质量的方法。该方法以群株生菜为研究对象,利用深度相机采集群株生菜俯视点云,将预处理后的点云数据输入实例分割模型Mask3D中训练,实现背景与生菜个体的实例分割,之后使用鲜质量预测网络预测个体生菜鲜质量。试验结果表明,该模型实现了个体生菜点云的分割提取,无多检和漏检的情况。当交并比(intersection over union,IoU)阈值为0.75时,群株生菜点云实例分割的精确度为0.924,高于其他实例分割模型;鲜质量预测网络实现了直接通过深度学习处理点云数据,预测个体生菜鲜质量的目的,预测结果的决定系数R2值为0.90,均方根误差值为12.42 g,优于从点云中提取特征量,再回归预测鲜质量的传统方法。研究结果表明该研究预测生菜鲜质量的精度较高,为利用俯视单面点云提取群株生菜中个体生菜表型参数提供了一种思路。
