Search Result

Select

Ensemble learning prediction of soybean yields in China based on meteorological data

LI Qian-chuan, XU Shi-wei, ZHUANG Jia-yu, LIU Jia-jia, ZHOU Yi, ZHANG Ze-xi

2023, 22 (6): 1909-1927. DOI: 10.1016/j.jia.2023.02.011

Abstract （207） PDF in ScienceDirect

The accurate prediction of soybean yield is of great significance for agricultural production, monitoring and early warning. Although previous studies have used machine learning algorithms to predict soybean yield based on meteorological data, it is not clear how different models can be used to effectively separate soybean meteorological yield from soybean yield in various regions. In addition, comprehensively integrating the advantages of various machine learning algorithms to improve the prediction accuracy through ensemble learning algorithms has not been studied in depth. This study used and analyzed various daily meteorological data and soybean yield data from 173 county-level administrative regions and meteorological stations in two principal soybean planting areas in China (Northeast China and the Huang–Huai region), covering 34 years. Three effective machine learning algorithms (K-nearest neighbor, random forest, and support vector regression) were adopted as the base-models to establish a high-precision and highly-reliable soybean meteorological yield prediction model based on the stacking ensemble learning framework. The model’s generalizability was further improved through 5-fold cross-validation, and the model was optimized by principal component analysis and hyperparametric optimization. The accuracy of the model was evaluated by using the five-year sliding prediction and four regression indicators of the 173 counties, which showed that the stacking model has higher accuracy and stronger robustness. The 5-year sliding estimations of soybean yield based on the stacking model in 173 counties showed that the prediction effect can reflect the spatiotemporal distribution of soybean yield in detail, and the mean absolute percentage error (MAPE) was less than 5%. The stacking prediction model of soybean meteorological yield provides a new approach for accurately predicting soybean yield.

Reference | Related Articles | Metrics

Select

The effects of soil properties, cropping systems and geographic location on soil prokaryotic communities in four maize production regions across China

TIAN Xue-liang, LIU Jia-jia, LIU Quan-cheng, XIA Xin-yao, PENG Yong, Alejandra I. HUERTA, YAN Jian-bing, LI Hui, LIU Wen-de

2022, 21 (7): 2145-2157. DOI: 10.1016/S2095-3119(21)63772-3

Abstract （225） PDF in ScienceDirect

The diversity of prokaryotic communities in soil is shaped by both biotic and abiotic factors. However, little is known about the major factors shaping soil prokaryotic communities at a large scale in agroecosystems. To this end, we undertook a study to investigate the impact of maize production cropping systems, soil properties and geographic location (latitude and longitude) on soil prokaryotic communities using metagenomic techniques, across four distinct maize production regions in China. Across all study sites, the dominant prokaryotes in soil were Alphaproteobacteria, Gammaproteobacteria, Betaproteobacteria, Gemmatimonadetes, Acidobacteria, and Actinobacteria. Non-metric multidimensional scaling revealed that prokaryotic communities clustered into the respective maize cropping systems in which they resided. Redundancy analysis (RDA) showed that soil properties especially pH, geographic location and cropping system jointly determined the diversity of the prokaryotic communities. The functional genes of soil prokaryotes from these samples were chiefly influenced by latitude, soil pH and cropping system, as revealed by RDA analysis. The abundance of genes in some metabolic pathways, such as genes involved in microbe–microbe interactions, degradation of aromatic compounds, carbon fixation pathways in prokaryotes and microbial metabolism were markedly different across the four maize production regions. Our study indicated that the combination of soil pH, cropping system and geographic location significantly influenced the prokaryotic community and the functional genes of these microbes. This work contributes to a deeper understanding of the composition and function of the soil prokaryotic community across large-scale production systems such as maize.

Reference | Related Articles | Metrics

Select

Morphological diversity and correlation analysis of phenotypes and quality traits of proso millet (Panicum miliaceum L.) core collections

ZHANG Da-zhong, Rabia Begum Panhwar, LIU Jia-jia, GONG Xiang-wei, LIANG Ji-bao, LIU Minxuan, LU Ping, GAO Xiao-li, FENG Bai-li

2019, 18 (5): 958-969. DOI: 10.1016/S2095-3119(18)61997-5

Abstract （208） PDF in ScienceDirect

Genetic diversity and comprehensive performance are the basis for the discovery and efficient use of proso millet (Panicum miliaceum L.) core collections. In this study, 386 proso millet core collections were used as materials to observe inflorescence color, leaf phase, inflorescence density, axis shape, branched spike length, panicle type, trichome, measured area of the top3 leaves, and chlorophyll content of the top3 leaves at filling stage. These core collections were also used to record growth period, plant height, diameter of main stem, plant tiller number, branch number, panicle length, panicle number per plant, and panicle weight per plant at the maturation stage. Starch, fat, protein, and yellow pigment contents in the grain and 1 000-seed weight were also measured after harvest. Then, quantitative traits were used for diversity analysis and comprehensive evaluation of each collection. Correlations between all traits were also analyzed. Results showed that among the 8 quality traits, the Shannon index (H´) of hull color was the highest (1.588) followed by the H´ of inflorescence density (0.984). However, inflorescence color and axis shape were lower. The H´ of 16 quantitative traits were significantly higher than the quality traits with the following traits having the highest indices: fat content (2.092), 1 000-seed weight (2.073), top3 leaves area (2.070), main stem diameter (2.056), and plant height (2.052). Furthermore, all other traits had a diversity higher than 1.900. After a comprehensive evaluation of phenotypic traits, plant height, diameter of main stem, plant tiller number, leaf area of top3 leaves, and 1 000-seed weight were the biggest contributors to the principal components. Six high-fat and high-protein cultivars, including Nuoshu, A75-2, Zhiduoaosizhi, Panlonghuangmi, Xiaobaishu, and Xiaohongshu were also screened. Correlations between the quantitative traits were significant, including the correlation between quality traits and quantitative traits. In conclusion, the core collections can be used as basis for discriminating among proso millet cultivars based on related traits and for further studies on millet with rich genetic diversity, good representation, and significant collection between traits.

Related Articles | Metrics

Select

Genetic diversity of Ustilago hordei in Tibetan areas as revealed by RAPD and SSR

ZHOU Yu, CHAO Gui-mei, LIU Jia-jia, ZHU Ming-qi, WANG Yang, FENG Bai-li

2016, 15 (10): 2299-2308. DOI: 10.1016/S2095-3119(16)61413-2

Abstract （1550） PDF in ScienceDirect

Covered smut, which is caused by Ustilago hordei (Pers.) Lagerh., is one of the most damaging diseases of highland barley (Hordeum vulgare Linn. var. nudum Hook. f) in Tibetan areas of China. To understand the molecular diversity of U. hordei, a total of 27 isolates, which were collected from highland barley plants from Tibet, Sichuan, Qinghai, and Gansu provinces/autonomous region, were analyzed using random amplified polymorphic DNA (RAPD) and simple sequence repeat (SSR) markers. Among the 100 RAPD primers used, 24 primers exhibited polymorphism. A total of 111 fragments were amplified, of which 103 were polymorphic with a polymorphic rate of 92.79%. The average observed number of alleles (Na), effective number of alleles (Ne), Nei’s genetic diversity (H), Shannon’s information index (I) and polymorphism information content (PIC) value in the RAPD markers were 1.9279, 1.5016, 0.2974, 0.4503 and 0.6428, respectively. For the SSR markers, 40 of the 111 primer pairs exhibited polymorphism and provided a total of 119 bands, of which 109 were polymorphic and accounted for 91.60% of the total bands. The Na, Ne, H, I and PIC values of the SSR markers were 1.9160, 1.4639, 0.2757, 0.4211 and 0.4340, respectively. The similarity coefficients ranged from 0.4957 to 0.9261 with an average of 0.7028 among all the 27 isolates used. The dendrogram, which was developed based on the RAPD and SSR combined marker dataset showed that the 27 U. hordei isolates were divided into 3 clusters at similarity coefficient of 0.7314. We determined that RAPD and SSR markers can be successfully used to assess the genetic variation among U. hordei isolates. The RAPD markers revealed higher levels of genetic polymorphism than did the SSR markers in this study. There existed a moderate genetic difference among isolates. The molecular variation and differentiation was somewhat associated with geographical origin but not for all of the isolates.

Reference | Related Articles | Metrics

About JIA

Editorial board

For authors