Prediction Models Based on Regression and Artificial Neural Network for Moduli of Layers Constituted by Open-Graded Aggregates

Lee, Yunje; Choi, Yong-Jin; Ahn, Dong-Hyun; Ahn, Jaehun

doi:10.3390/ma14051199

Cited by 4 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ANNs can be used wherever simple mathematical models are not applicable due to the complexity of the systems under consideration. This tool has also been widely used in stormwater management studies [59,60]. Multilayer perception (MLP) networks [58] were used in this research.…”

Section: Evaluation Of the Influence Of Catchment Parameters On The R...mentioning

confidence: 99%

Evaluation of the Influence of Catchment Parameters on the Required Size of a Stormwater Infiltration Facility

Kordana-Obuch

Starzec

Słyś

2023

Water

View full text Add to dashboard Cite

One sustainable method of stormwater management is surface infiltration with retention. Proper design of stormwater infiltration facilities ensures a reduction in flood risk within urban catchments. However, this is not possible without considering the key design parameters of such facilities. The aim of this paper is to determine the influence of the parameters characterizing the catchment area on the size of the stormwater infiltration facilities. The research used SWMM 5.1 and Statistica software. It was carried out on the example of model catchments and a real urban catchment. The analysis showed that it is of key importance in the design of stormwater infiltration facilities to accurately determine the total catchment area, the type of soil within it, and the proportion of impervious surfaces. The relevance of the other parameters that characterize the catchment area is clearly lesser. However, they cannot be completely ignored, and their values should be determined as accurately as possible. These research results can guide stakeholders in the decision-making process during investment planning and implementation.

show abstract

Section: Evaluation Of the Influence Of Catchment Parameters On The R...mentioning

confidence: 99%

Evaluation of the Influence of Catchment Parameters on the Required Size of a Stormwater Infiltration Facility

Kordana-Obuch

Starzec

Słyś

2023

Water

View full text Add to dashboard Cite

show abstract

“…One of the promises of a digital twin in crop management is for the automatic prediction system to support in deciding the appropriate fertilization period [22][23][24]. Deploying the sensors which monitor the concentration of nutrients present in soil, humidity, and temperature in the real fields to make consistent quality checks.…”

Section: Literature Reviewmentioning

confidence: 99%

A Concentration Prediction-Based Crop Digital Twin Using Nutrient Co-Existence and Composition in Regression Algorithms

Ghazvini,

Sharef,

Balasundram

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Crop digital twin is redefining traditional farming practices, offering unprecedented opportunities for real-time monitoring, predictive and simulation analysis, and optimization. This research embarks on an exploration of the synergy between precision agriculture, crop modeling, and regression algorithms to create a digital twin for farmers to augment the concentration and composition prediction-based crop nutrient recovery. This captures the holistic representation of crop characteristics, considering the intricate relationships between environmental factors, nutrient concentrations, and crop compositions. However, the complexity arising from diverse soil and environmental conditions makes nutrient content analysis expensive and time-consuming. This paper presents two approaches, namely, (i) single-nutrient concentration prediction and (ii) nutrient composition concentration prediction, which is the result of a predictive digital twin case study that employs six regression algorithms, namely, Elastic Net, Polynomial, Stepwise, Ridge, Lasso, and Linear Regression, to predict rice nutrient content efficiently, particularly considering the coexistence and composition of multiple nutrients. Our research findings highlight the superiority of the Polynomial Regression model in predicting nutrient content, with a specific focus on accurate nitrogen percentage prediction. This insight can be used for nutrient recovery intervention by knowing the precise amount of nutrient to be added into the crop medium. The adoption of the Polynomial Regression model offers a valuable tool for nutrient management practices in the crop digital twin, potentially resulting in higher-quality rice production and a reduced environmental impact. The proposed method can be replicable in other low-resourced crop digital twin system.

show abstract

“…Another study used regression methods and found that random forest regression algorithms provided the highest accuracy for estimating rice shoot dry matter, leaf area index, and nitrogen accumulation [11]. A third study evaluated different approaches for estimating rice aboveground biomass, plant nitrogen uptake, and nitrogen nutrition index, with the random forest algorithm demonstrating superior performance [12]. An additional study focused on using machine learning for early detection of nutrient deficiency in rice through leaf image processing, achieving high testing accuracy and roc_auc score [4].…”

Section: Literature Reviewmentioning

confidence: 99%

Concentration Prediction‐Based Crop Digital Twin Using Nutrient Co‐Existence and Composition in Regression Algorithms

Ghazvini,

Sharef

2023

Preprint

View full text Add to dashboard Cite

Crop digital twin is redefining traditional farming practices, offering unprecedented opportunities for real-time monitoring, predictive and simulation analysis, and optimization. This research embarks on an exploration of the synergy between precision agriculture, crop modeling, and regression algorithms to create a digital twin for augmenting farmers the concentration and composition prediction-based crop nutrient recovery. This captures the holistic representation of crop characteristics, considering the intricate relationships between environmental factors, nutrient concentrations, and crop compositions. However, the complexity arising from diverse soil and environmental conditions makes nutrient content analysis expensive and time-consuming. This paper presents the result of a predictive digital twin case study that employs six regression algorithms namely Elastic Net, Polynomial, Stepwise, Ridge, Lasso, and Linear Regression to predict rice nutrient content efficiently, particularly considering the coexistence and composition of multiple nutrients. Our research findings highlight the superiority of the Polynomial Regression model in predicting nutrient content, with a specific focus on accurate nitrogen percentage prediction. This insight can be used for nutrient recovery intervention by knowing the precise amount of nutrient to be added into the crop medium. The adoption of the Polynomial Regression model offers a valuable tool for nutrient management practices in the crop digital twin, potentially resulting in higher-quality rice production and a reduced environmental impact. The proposed method can be replicable in other low-resourced crop digital twin system.

show abstract

Prediction Models Based on Regression and Artificial Neural Network for Moduli of Layers Constituted by Open-Graded Aggregates

Cited by 4 publications

References 31 publications

Evaluation of the Influence of Catchment Parameters on the Required Size of a Stormwater Infiltration Facility

Evaluation of the Influence of Catchment Parameters on the Required Size of a Stormwater Infiltration Facility

A Concentration Prediction-Based Crop Digital Twin Using Nutrient Co-Existence and Composition in Regression Algorithms

Concentration Prediction‐Based Crop Digital Twin Using Nutrient Co‐Existence and Composition in Regression Algorithms

Contact Info

Product

Resources

About