Dataset Information

Drought stress detection technique for wheat crop using machine learning.

ABSTRACT: The workflow of this research is based on numerous hypotheses involving the usage of pre-processing methods, wheat canopy segmentation methods, and whether the existing models from the past research can be adapted to classify wheat crop water stress. Hence, to construct an automation model for water stress detection, it was found that pre-processing operations known as total variation with L1 data fidelity term (TV-L1) denoising with a Primal-Dual algorithm and min-max contrast stretching are most useful. For wheat canopy segmentation curve fit based K-means algorithm (Cfit-kmeans) was also validated for the most accurate segmentation using intersection over union metric. For automated water stress detection, rapid prototyping of machine learning models revealed that there is a need only to explore nine models. After extensive grid search-based hyper-parameter tuning of machine learning algorithms and 10 K fold cross validation it was found that out of nine different machine algorithms tested, the random forest algorithm has the highest global diagnostic accuracy of 91.164% and is the most suitable for constructing water stress detection models.

SUBMITTER: Gupta A

PROVIDER: S-EPMC10280683 | biostudies-literature | 2023

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Drought stress detection technique for wheat crop using machine learning.

Gupta Ankita A Kaur Lakhwinder L Kaur Gurmeet G

PeerJ. Computer science 20230519

The workflow of this research is based on numerous hypotheses involving the usage of pre-processing methods, wheat canopy segmentation methods, and whether the existing models from the past research can be adapted to classify wheat crop water stress. Hence, to construct an automation model for water stress detection, it was found that pre-processing operations known as total variation with L1 data fidelity term (TV-L1) denoising with a Primal-Dual algorithm and min-max contrast stretching are mo ...[more]

PMID: 37346648

Similar Datasets

Project description:BackgroundWheat, an important cereal crop, is commonly cultivated in arid and semiarid areas, and therefore, it often experiences water deficit conditions. The consequences of induced stress on wheat can be mitigated through vermicompost amendments. To address drought stress on wheat seedlings, a pot experiment was conducted in the wire-house in which two contrasting wheat cultivars, Faisalabad-08 (drought-tolerant) and Galaxy-13 (drought-sensitive), were exposed to three water level conditions: well-watered [D0, 70% of field capacity (FC)], moderate drought (D1, 45% FC), and severe drought (D2, 30% FC). Four rates of vermicompost, derived from cow dung enriched with cellulolytic microbes, were applied (VT0, control; VT1, 4 t ha-1; VT2, 6 t ha-1; and VT3, 8 t ha-1) to the experiment. Data on various physiological, biochemical, and enzymatic antioxidants were recorded.ResultsOur results demonstrated that the drought treatments significantly reduced nutrient accumulation, chlorophyll and SPAD values, and carotenoid content in both cultivars where the maximum reduction was recorded for severe drought stress. Nonetheless, the application of vermicompost significantly improved these traits, and statistically maximum chlorophyll contents, SPAD value, and total carotenoid contents were observed for VT1 in both cultivars under drought treatments. While the lowest chlorophyll and carotenoid contents were recorded for untreated replicated pots. Among the cultivars, Faisalabad-08 exhibited greater resistance to drought, as evidenced by higher values of the aforementioned traits compared to Galaxy-13. Soil-applied vermicompost also showed a positive influence on antioxidant enzyme activities in both wheat cultivars grown under well-watered as well as water-scarce conditions.ConclusionsThe findings of this study revealed that drought conditions substantially decreased the enzymatic antioxidants and physiological and biochemical attributes of the wheat crop. However, soil-applied vermicompost, particularly at an optimum rate, had a positive impact on the wheat seedlings under drought conditions. Moving forward, exploring the potential of utilizing cellulolytic microbe-enriched cow dung vermicompost stands as a promising avenue to mitigate the detrimental effects of water stress on wheat. Further research in this direction could offer substantial insights into enhancing wheat resilience and productivity under water stress conditions.

Project description:Evaluating crop health and forecasting yields in the early stages are crucial for effective crop and market management during periods of biotic stress for both farmers and policymakers. Field experiments were conducted during 2017-18 and 2018-19 with objective to evaluate the effect of yellow rust on various biophysical parameters of 24 wheat cultivars, with varying levels of resistance to yellow rust and to develop machine learning (ML) models with improved accuracy for predicting yield by integrating thermal and RGB indices with crucial plant biophysical parameters. Results revealed that as the level of rust increased, so did the canopy temperature and there was a significant decrease in crop photosynthesis, transpiration, stomatal conductance, leaf area index, membrane stability index, relative leaf water content, and normalized difference vegetation index due to rust, and the reductions were directly correlated with levels of rust severity. The yield reduction in moderate resistant, low resistant and susceptible cultivars as compared to resistant cultivars, varied from 15.9-16.9%, 28.6-34.4% and 59-61.1%, respectively. The ML models were able to provide relatively accurate early yield estimates, with the accuracy increasing as the harvest approached. The yield prediction performance of the different ML models varied with the stage of the crop growth. Based on the validation output of different ML models, Cubist, PLS, and SpikeSlab models were found to be effective in predicting the wheat yield at an early stage (55-60 days after sowing) of crop growth. The KNN, Cubist, SLR, RF, SpikeSlab, XGB, GPR and PLS models were proved to be more useful in predicting the crop yield at the middle stage (70 days after sowing) of the crop, while RF, SpikeSlab, KNN, Cubist, ELNET, GPR, SLR, XGB and MARS models were found good to predict the crop yield at late stage (80 days after sowing). The study quantified the impact of different levels of rust severity on crop biophysical parameters and demonstrated the usefulness of remote sensing and biophysical parameters data integration using machine-learning models for early yield prediction under biotically stressed conditions.

Dataset Information

Drought stress detection technique for wheat crop using machine learning.

Publications

Drought stress detection technique for wheat crop using machine learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets