A Stochastic Optimization Model for Agricultural Irrigation Water Allocation Based on the Field Water Cycle

Yan, Zehao; Li, Mo

doi:10.3390/w10081031

Cited by 12 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Devising an accurate mathematical crop evapotranspiration (ET) model is fundamental to improving crop water use efficiency and thus important in developing a practical irrigation system for a greenhouse [ 1 , 2 ]. Evapotranspiration is an important parameter in the study of dynamic change in a field water cycle [ 3 ] and energy balance [ 4 ] and is therefore of great concern in agricultural production.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Greenhouse Tomato Crop Evapotranspiration Using XGBoost Machine Learning Model

Zhao

et al. 2022

Plants

View full text Add to dashboard Cite

Crop evapotranspiration estimation is a key parameter for achieving functional irrigation systems. However, ET is difficult to directly measure, so an ideal solution was to develop a simulation model to obtain ET. There are many ways to calculate ET, most of which use models based on the Penman–Monteith equation, but they are often inaccurate when applied to greenhouse crop evapotranspiration. The use of machine learning models to predict ET has gradually increased, but research into their application for greenhouse crops is relatively rare. We used experimental data for three years (2019–2021) to model the effects on ET of eight meteorological factors (net solar radiation (Rn), mean temperature (Ta), minimum temperature (Tamin), maximum temperature (Tamax), relative humidity (RH), minimum relative humidity (RHmin), maximum relative humidity (RHmax), and wind speed (V)) using a greenhouse drip irrigated tomato crop ET prediction model (XGBR-ET) that was based on XGBoost regression (XGBR). The model was compared with seven other common regression models (linear regression (LR), support vector regression (SVR), K neighbors regression (KNR), random forest regression (RFR), AdaBoost regression (ABR), bagging regression (BR), and gradient boosting regression (GBR)). The results showed that Rn, Ta, and Tamax were positively correlated with ET, and that Tamin, RH, RHmin, RHmax, and V were negatively correlated with ET. Rn had the greatest correlation with ET (r = 0.89), and V had the least correlation with ET (r = 0.43). The eight models were ordered, in terms of prediction accuracy, XGBR-ET > GBR-ET > SVR-ET > ABR-ET > BR-ET > LR-ET > KNR-ET > RFR-ET. The statistical indicators mean square error (0.032), root mean square error (0.163), mean absolute error (0.132), mean absolute percentage error (4.47%), and coefficient of determination (0.981) of XGBR-ET showed that XGBR-ET modeled daily ET for greenhouse tomatoes well. The parameters of the XGBR-ET model were ablated to show that the order of importance of meteorological factors on XGBR-ET was Rn > RH > RHmin> Tamax> RHmax> Tamin> Ta> V. Selecting Rn, RH, RHmin, Tamax, and Tamin as model input variables using XGBR ensured the prediction accuracy of the model (mean square error 0.047). This study has value as a reference for the simplification of the calculation of evapotranspiration for drip irrigated greenhouse tomato crops using a novel application of machine learning as a basis for an effective irrigation program.

show abstract

Section: Introductionmentioning

confidence: 99%

Prediction of Greenhouse Tomato Crop Evapotranspiration Using XGBoost Machine Learning Model

Zhao

et al. 2022

Plants

View full text Add to dashboard Cite

show abstract

“…This study contributes to the literature by evaluating how weather variations in a changing climate, unknown at the moment that decisions are taken, affect sustainable nutrient management practices. To this purpose, we draw on methods from stochastic optimization, which have recently been applied in the field of agricultural hydrology and irrigation management [21,22]. A small number of stochastic optimization models exist that deal with nutrient pollution, for instance for Lake Balaton in Central Europe and Erhai Lake in China, but these studies do not consider climate change [23,24].…”

Section: Introductionmentioning

confidence: 99%

Containing the Risk of Phosphorus Pollution in Agricultural Watersheds

et al. 2022

View full text Add to dashboard Cite

Phosphorus (P) is an essential nutrient to boost crop yields, but P runoff can cause nutrient over-enrichment in agricultural watersheds and can lead to irreversible effects on aquatic ecosystems and their biodiversity. Lake Erie is one prominent example as this watershed has experienced multiple episodes of harmful algal blooms over the last decades. Annual P loads crucially depend on yearly weather variations, which can create the risk of years with high runoff and excessive nutrient loads. Here we apply stochastic modeling to derive sustainable management strategies that balance crop yield optimization with environmental protection, while accounting for weather variability as well as weather trends as a result of climate change. We demonstrate that ignoring annual weather variations results in mitigation efforts for environmental pollution that are largely insufficient. Accounting explicitly for future variations in precipitation allows us to control the risk of emissions exceeding the P target loads. When realistic risk targets are imposed, we find that a package of additional measures is required to avoid P over-enrichment in the Lake Erie watershed. This package consists of a substantial reduction of P inputs (approximately 30% for different accepted risk levels), adoption of cover crops throughout the near- and mid-century, and cultivation of less nutrient-intensive crops (30% more soy at the expense of corn). Although climate change reinforces these conclusions, we find that the accepted risk level of exceeding P target loads is the predominant factor in defining a sustainable nutrient management policy.

show abstract

“…There is another study by Zehao and Li (2018) in which they expanded a two-stage chance-limited programming approach with accidental variables on both the left and right sides of boundaries for agricultural irrigation water allocation in the district of Yingke, in the centre of the Heihe River basin, north-west China. Their model has the capacity to introduce logical irrigation allocation rules by paying attention to all these aspects: water transformation among crops, evapotranspiration, precipitation, irrigation, soil water content and deep percolation.…”

mentioning

confidence: 99%

Optimal water allocation and distribution management in irrigation networks under uncertainty by multi‐stage stochastic case study: Irrigation and drainage networks of Maroon^*

Behbahani

Moghaddasi

Ebrahimi

et al. 2020

Irrigation and Drainage

View full text Add to dashboard Cite

In the present research the aim was to prepare a spatial and temporal optimization model for allocating irrigation water and cropping pattern in the Maroon irrigation and drainage networks, which are located in the province of Khoozestan, under uncertainty. Hydrometrical data were gathered from the Maroon network station. Meteorological data were prepared from Idenak station in Behbahan City during 2006-2016. Therefore a model was designed and developed to maximize the total gross benefit of the irrigation networks of Maroon. The presented model is capable of adjusting the optimal water distribution among networks, crops and their different growing stages, determining water shortage, allocating surplus water, and the gross benefit under three scenarios of arid, normal and wet years in two sub-models of actual intra-network optimal management and optimal management from the reservoir output to the inside network by applying multi-stage stochastic programming under uncertainty. The findings show the priority of the second sub-model over the first run. In the upper and lower bounds model it was illustrated that the cropping areas were increased by respectively 33 and 19%, and of course the benefit amount had an increase of 67 and 7% in the second sub-model. K E Y W O R D S irrigation water allocation, multi-stage stochastic programming, spatial and temporal optimization, uncertainty Résumé Dans la présente recherche, l'objectif était de préparer un modèle d'optimisation spatiale et temporelle pour l'allocation de l'eau d'irrigation et le modèle de culture dans les réseaux d'irrigation et de drainage de Maroon, qui sont situés dans la province du Khoozestan, sous incertitude. Des données * Gestion optimale de l'allocation et de la distribution de l'eau dans les réseaux d'irrigation en cas d'incertitude par la méthode stochastique à plusieurs niveaux. Étude de cas: réseaux d'irrigation et de drainage de Marun.

show abstract

A Stochastic Optimization Model for Agricultural Irrigation Water Allocation Based on the Field Water Cycle

Cited by 12 publications

References 23 publications

Prediction of Greenhouse Tomato Crop Evapotranspiration Using XGBoost Machine Learning Model

Prediction of Greenhouse Tomato Crop Evapotranspiration Using XGBoost Machine Learning Model

Containing the Risk of Phosphorus Pollution in Agricultural Watersheds

Optimal water allocation and distribution management in irrigation networks under uncertainty by multi‐stage stochastic case study: Irrigation and drainage networks of Maroon^*

Contact Info

Product

Resources

About

A Stochastic Optimization Model for Agricultural Irrigation Water Allocation Based on the Field Water Cycle

Cited by 12 publications

References 23 publications

Prediction of Greenhouse Tomato Crop Evapotranspiration Using XGBoost Machine Learning Model

Prediction of Greenhouse Tomato Crop Evapotranspiration Using XGBoost Machine Learning Model

Containing the Risk of Phosphorus Pollution in Agricultural Watersheds

Optimal water allocation and distribution management in irrigation networks under uncertainty by multi‐stage stochastic case study: Irrigation and drainage networks of Maroon*

Contact Info

Product

Resources

About

Optimal water allocation and distribution management in irrigation networks under uncertainty by multi‐stage stochastic case study: Irrigation and drainage networks of Maroon^*