期刊文献+
共找到2篇文章
< 1 >
每页显示 20 50 100
Improving the phenotypic expression of rice genotypes:Rethinking “intensification” for production systems and selection practices for rice breeding 被引量:3
1
作者 Norman Uphoff Vasilia Fasoula +2 位作者 Anas Iswandi Amir Kassam Amod K.Thakur 《The Crop Journal》 SCIE CAS CSCD 2015年第3期174-189,共16页
Intensification in rice crop production is generally understood as requiring increased use of material inputs: water, inorganic fertilizers, and agrochemicals. However, this is not the only kind of intensification ava... Intensification in rice crop production is generally understood as requiring increased use of material inputs: water, inorganic fertilizers, and agrochemicals. However, this is not the only kind of intensification available. More productive crop phenotypes, with traits such as more resistance to biotic and abiotic stresses and shorter crop cycles, are possible through modifications in the management of rice plants, soil, water, and nutrients, reducing rather than increasing material inputs. Greater factor productivity can be achieved through the application of new knowledge and more skill, and(initially) more labor, as seen from the System of Rice Intensification(SRI), whose practices are used in various combinations by as many as 10 million farmers on about 4 million hectares in over 50 countries. The highest yields achieved with these management methods have come from hybrids and improved rice varieties, confirming the importance of making genetic improvements. However,unimproved varieties are also responsive to these changes, which induce better growth and functioning of rice root systems and more abundance, diversity, and activity of beneficial soil organisms. Some of these organisms as symbiotic endophytes can affect and enhance the expression of rice plants' genetic potential as well as their phenotypic resilience to multiple stresses, including those of climate change. SRI experience and data suggest that decades of plant breeding have been selecting for the best crop genetic endowments under suboptimal growing conditions, with crowding of plants that impedes their photosynthesis and growth, flooding of rice paddies that causes roots to degenerate and forgoes benefits derived from aerobic soil organisms, and overuse of agrochemicals that adversely affect these organisms as well as soil and human health. This review paper reports evidence from research in India and Indonesia that changes in crop and water management can improve the expression of rice plants' genetic potential, thereby creating more producti 展开更多
关键词 EXPRESSION of genetic potential rice phenotypes SELECTION criteria for plant breeding SELECTION efficiency System of rice INTENSIFICATION
下载PDF
基于Random Forest的水稻细菌性条斑病识别方法研究 被引量:11
2
作者 袁培森 曹益飞 +2 位作者 马千里 王浩云 徐焕良 《农业机械学报》 EI CAS CSCD 北大核心 2021年第1期139-145,208,共8页
为了快速、准确、有效地识别发病早期的细菌性条斑病,提出基于随机森林(Random forest,RF)算法的水稻细菌性条斑病识别方法,利用光谱成像技术获取该病害的高光谱数据,通过多元散射校正减少和消除噪声及基线漂移对光谱数据的不利影响。... 为了快速、准确、有效地识别发病早期的细菌性条斑病,提出基于随机森林(Random forest,RF)算法的水稻细菌性条斑病识别方法,利用光谱成像技术获取该病害的高光谱数据,通过多元散射校正减少和消除噪声及基线漂移对光谱数据的不利影响。利用随机森林特征重要性指标,选取逻辑回归(LR)、朴素贝叶斯(NB)、决策树(DT)、支持向量分类机(SVC)、k最近邻(KNN)和梯度提升决策树(Gradient boosting decision tree,GBDT)算法进行对比试验。同时筛选出12个位于450~664 nm范围内对识别模型有重要影响的光谱波段,并与全波段进行分类结果比较。试验结果表明:RF算法的分类准确率为95.24%,与试验选取的其他算法相比,效果最优,比NB准确率提高了20.97个百分点;与全波段分类结果相比,利用RF算法基于12个波长的识别,波长数减少了98.05%,识别精确率为94.66%,召回率为99.55%,F1值为97.04%,准确率为94.32%。虽然精确率减少了2.97个百分点、准确率减少了0.85个百分点,但召回率增加了4.4个百分点、F1值增加了0.67个百分点,模型精度满足要求。 展开更多
关键词 水稻表型 随机森林 高光谱成像 细菌性条斑病 病害识别
下载PDF
上一页 1 下一页 到第
使用帮助 返回顶部