Dataset Information

Determining the most important physiological and agronomic traits contributing to maize grain yield through machine learning algorithms: a new avenue in intelligent agriculture.

ABSTRACT: Prediction is an attempt to accurately forecast the outcome of a specific situation while using input information obtained from a set of variables that potentially describe the situation. They can be used to project physiological and agronomic processes; regarding this fact, agronomic traits such as yield can be affected by a large number of variables. In this study, we analyzed a large number of physiological and agronomic traits by screening, clustering, and decision tree models to select the most relevant factors for the prospect of accurately increasing maize grain yield. Decision tree models (with nearly the same performance evaluation) were the most useful tools in understanding the underlying relationships in physiological and agronomic features for selecting the most important and relevant traits (sowing date-location, kernel number per ear, maximum water content, kernel weight, and season duration) corresponding to the maize grain yield. In particular, decision tree generated by C&RT algorithm was the best model for yield prediction based on physiological and agronomical traits which can be extensively employed in future breeding programs. No significant differences in the decision tree models were found when feature selection filtering on data were used, but positive feature selection effect observed in clustering models. Finally, the results showed that the proposed model techniques are useful tools for crop physiologists to search through large datasets seeking patterns for the physiological and agronomic factors, and may assist the selection of the most important traits for the individual site and field. In particular, decision tree models are method of choice with the capability of illustrating different pathways of yield increase in breeding programs, governed by their hierarchy structure of feature ranking as well as pattern discovery via various combinations of features.

SUBMITTER: Shekoofa A

PROVIDER: S-EPMC4022653 | biostudies-literature | 2014

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Determining the most important physiological and agronomic traits contributing to maize grain yield through machine learning algorithms: a new avenue in intelligent agriculture.

Shekoofa Avat A Emam Yahya Y Shekoufa Navid N Ebrahimi Mansour M Ebrahimie Esmaeil E

PloS one 20140515 5

Prediction is an attempt to accurately forecast the outcome of a specific situation while using input information obtained from a set of variables that potentially describe the situation. They can be used to project physiological and agronomic processes; regarding this fact, agronomic traits such as yield can be affected by a large number of variables. In this study, we analyzed a large number of physiological and agronomic traits by screening, clustering, and decision tree models to select the ...[more]

PMID: 24830330

Similar Datasets

Project description:BackgroundThe combination of mulch with N fertilizer application is a common agronomic technique used in the production of rainfed maize (Zea mays L.) to achieve higher yields under conditions of optimum planting density and adequate N supply. However, the combined effects of mulch, planting density, and N fertilizer application rate on plant N uptake and N translocation efficiency are not known. The objective of this study was to quantify the interaction effect of mulch, planting density, and N fertilizer application rate on maize grain yield, N uptake, N translocation, and N translocation efficiency. The experiment was arranged in a randomized complete block design with three factors (2 mulch levels × 2 planting densities × 4 N fertilizer application rates) replicated four times.ResultsThere was a significant interaction among mulch, plant density, and N fertilizer on maize grain yield, kernel number per cob, N uptake, N translocation, and N translocation efficiency. Averaged over the 3 years of the study, total plant N uptake at silking ranged from 79 to 149 kg N ha- 1 with no mulch and from 76 to 178 kg N ha- 1 with mulch. The N uptake at silking in different plant organs ranked as leaf > grain > stem > cob. Averaged across all factors, the highest N translocation was observed in leaves, which was 59.4 and 88.7% higher than observed in stems and ears, respectively. The mean vegetative organ N translocation efficiency averaged over mulch, planting density, and N fertilizer application rate treatments decreased in the order of leaf > stem > cob.ConclusionsMulch, planting density, and N fertilizer application rate not only have significant effects on improving maize grain yield and NUE, but also on N uptake, N translocation, and N translocation efficiency. Our results showed clearly that under high planting density, the combination of mulch and moderate N fertilizer application rate was the optimal strategy for increasing maize grain yield and N use efficiency.

Project description:AimsThe aim of the present study was to evaluate the performance of 'high'-'low' yielding pyramided lines (PLs), having the same combinations of qDTYs in Samba Mahsuri, MR219 and IR64-Sub1 genetic backgrounds, and to understand the genetic interactions among QTL and/with genetic background affecting grain yield.BackgroundEpistasis regulates the expression of traits governed by several major/minor genes/QTL. Multiple pyramided lines (PLs) with the same grain yield QTL (qDTYs) combinations but possessing grain yield variability under different levels of reproductive stage drought stress were identified in different rice genetic backgrounds at International Rice Research Institute (IRRI).ObjectivesThe objectives of the present study were to evaluate the performance pyramided lines (PLs) with drought QTL in the backgrounds of Samba Mahsuri, MR219 and IR64-Sub1 under reproductive stage drought stress (RS) and NS (non-stress) conditions, to understand the effect of epistatic interactions among qDTYs and with genetic background on GY under the differential level of stress and to identify the promising drought-tolerant lines with high yield under drought and higher background recovery in different genetic backgrounds.MethodsThe experiments were conducted in 2015 DS (dry season), 2015 WS (wet season) and 2017 DS at IRRI, Los Baños, Philippines, in a transplanted lowland ecosystem under lowland severe stress (LSS), lowland moderate stress (LMS) and lowland non-stress (LNS). The experiments were laid out in alpha lattice design with two replications.ResultsSeveral digenic interactions were found in different genetic backgrounds, 13 interactions in Samba Mahsuri, 11 in MR219 and 20 in IR64-Sub1 backgrounds. Among all digenic interactions, one QTL × QTL interaction, 17 QTL × background and 26 background × background interactions resulted in GY reduction in low yielding PLs in different genetic backgrounds under LSS or LMS. Negative interaction of qDTY3.1 , qDTY4.1 and qDTY9.1 with background markers and background × background interactions caused up to 15% GY reduction compared to the high yielding PLs under LMS in the Samba Mahsuri PLs. In MR219 PLs, the negative interaction of qDTY2.2 , qDTY3.2 , qDTY4.1 and qDTY12.1 with the background marker interval RM314-RM539, RM273-RM349 and RM445-RM346, RM473D-RM16, respectively resulted 52% GY reduction compared to the high yielding PLs under LSS. In IR64-Sub1 PLs, qDTY6.1 interacted with background loci at RM16-RM135, RM228-RM333, RM202-RM287 and RM415-RM558A marker interval under LSS and at RM475-RM525 marker interval under LMS, causing GY reduction to 58% compared to the high yielding PLs.ConclusionHigh yielding PLs in Samba Mahsuri (IR 99734:1-33-69-1-22-6), MR219 (IR 99784-156-87-2-4-1) and IR64-Sub1 (IR 102784:2-89-632-2-1-2) backgrounds without any negative interactions were identified. The identified selected promising PLs may be used as potential drought-tolerant donors or may be released as varieties for drought-prone ecosystems in different countries.

Dataset Information

Determining the most important physiological and agronomic traits contributing to maize grain yield through machine learning algorithms: a new avenue in intelligent agriculture.

Publications

Determining the most important physiological and agronomic traits contributing to maize grain yield through machine learning algorithms: a new avenue in intelligent agriculture.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets