Recent publications have highlighted the development of an alternate cotton-peanut intercropping as a novel strat-egy to enhance agricultural productivity.In this article,we provide an overview of the progress made in...Recent publications have highlighted the development of an alternate cotton-peanut intercropping as a novel strat-egy to enhance agricultural productivity.In this article,we provide an overview of the progress made in the alternate cotton-peanut intercropping,specifically focusing on its yield benefits,environmental impacts,and the underlying mechanisms.In addition,we advocate for future investigations into the selection or development of appropriate crop varieties and agricultural equipment,pest management options,and the mechanisms of root-canopy interactions.This review is intended to provide a valuable reference for understanding and adopting an alternate intercropping system for sustainable cotton production.展开更多
我国人多地少,持续提高花生产量是花生栽培的首要目标。建国以来,我国花生高产栽培技术研究与应用取得了长足的进步,形成了独具中国特色的花生高产栽培技术体系,带动了花生整体生产水平的不断提高。回顾和总结我国花生高产栽培历程和经...我国人多地少,持续提高花生产量是花生栽培的首要目标。建国以来,我国花生高产栽培技术研究与应用取得了长足的进步,形成了独具中国特色的花生高产栽培技术体系,带动了花生整体生产水平的不断提高。回顾和总结我国花生高产栽培历程和经验,分析和探讨花生持续增产潜力与途径,有助于进一步提升我国花生高产栽培研究创新能力和整体生产水平。20世纪70年代初期,通过应用增产效果显著的氮磷化肥施用技术,产量突破了6000 kg hm^(-2);70年代末,通过化学调控、地膜覆盖、氮磷钾平衡施肥等关键技术,产量突破了7500 kg hm^(-2);进入20世纪90年代后,通过缓控徒长、量化施肥等关键技术,产量突破了9000kghm^(-2);进入新千年后,通过单粒精播等关键技术,产量突破了11,250 kg hm^(-2);2023年,以单粒精播技术为核心,配套全程可控施肥、“三防三促”群体调控和微生物耦合技术等,构建高产栽培技术体系创造实打验收12,982 kg hm^(-2)的全国高产纪录。据推算花生实际生产能力还有较大的提升空间,培育高潜力品种、充分挖掘土壤生产潜能和构建高质量的群体是未来进一步提高花生产量的主要途径。展开更多
传统CNN算法在花生荚果外观识别任务中存在内存密集型和计算密集型问题,以及其在资源受限的边缘终端上部署困难,基于此,该研究提出了一种高效的花生荚果识别模型——PPINET(peanut pod identification network),以适应嵌入式设备的资源...传统CNN算法在花生荚果外观识别任务中存在内存密集型和计算密集型问题,以及其在资源受限的边缘终端上部署困难,基于此,该研究提出了一种高效的花生荚果识别模型——PPINET(peanut pod identification network),以适应嵌入式设备的资源限制需求。该模型通过结合深度可分离卷积和倒残差结构显著降低参数量和计算量,同时保留特征提取能力,并引入MQA(multi-query attention)模块增强关键特征提取,并利用TuNAS(easy-to-tune and scalable implementation of efficient neural architecture search with weight sharing)策略优化模型结构,使其在资源受限设备上表现优异。此外,采用ResNet(residual neural network)进行知识蒸馏配合三折交叉验证训练提升精度,最终量化为RKNN格式并在瑞芯微RK3588上实现NPU加速部署。PPINET模型尺寸仅为1.85 MB,参数量为0.49 M,浮点运算数为0.30G。PPINET在花生荚果分类中表现优异,准确率达98.65%,在RK3588上推理速度达321 fps。该模型具备较高的识别准确率和快速的识别速度,能够实现花生荚果的实时精准检测。展开更多
基金National Natural Science Foundation of China(32101844)Shandong Provincial Natural Science Foundation(ZR2021QC188 and ZR2022MC103).
文摘Recent publications have highlighted the development of an alternate cotton-peanut intercropping as a novel strat-egy to enhance agricultural productivity.In this article,we provide an overview of the progress made in the alternate cotton-peanut intercropping,specifically focusing on its yield benefits,environmental impacts,and the underlying mechanisms.In addition,we advocate for future investigations into the selection or development of appropriate crop varieties and agricultural equipment,pest management options,and the mechanisms of root-canopy interactions.This review is intended to provide a valuable reference for understanding and adopting an alternate intercropping system for sustainable cotton production.
文摘我国人多地少,持续提高花生产量是花生栽培的首要目标。建国以来,我国花生高产栽培技术研究与应用取得了长足的进步,形成了独具中国特色的花生高产栽培技术体系,带动了花生整体生产水平的不断提高。回顾和总结我国花生高产栽培历程和经验,分析和探讨花生持续增产潜力与途径,有助于进一步提升我国花生高产栽培研究创新能力和整体生产水平。20世纪70年代初期,通过应用增产效果显著的氮磷化肥施用技术,产量突破了6000 kg hm^(-2);70年代末,通过化学调控、地膜覆盖、氮磷钾平衡施肥等关键技术,产量突破了7500 kg hm^(-2);进入20世纪90年代后,通过缓控徒长、量化施肥等关键技术,产量突破了9000kghm^(-2);进入新千年后,通过单粒精播等关键技术,产量突破了11,250 kg hm^(-2);2023年,以单粒精播技术为核心,配套全程可控施肥、“三防三促”群体调控和微生物耦合技术等,构建高产栽培技术体系创造实打验收12,982 kg hm^(-2)的全国高产纪录。据推算花生实际生产能力还有较大的提升空间,培育高潜力品种、充分挖掘土壤生产潜能和构建高质量的群体是未来进一步提高花生产量的主要途径。
