Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Bücher
Zeitschriften
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
SLX-Digitalkonferenz: Zukunftswerkstatt 2024

Mehr Umsatz mit Top-Kontakten

Am 7. Mai erfahren Sie, wie Vertriebsteams Leadgenerierung, Leadnurturing und Leadstrategien effizient steuern können.
Erweiterte Suche
Anmelden
nach oben

2023 | Buch

The Importance of Agricultural and Meteorological Predictions Using Machine Learning Models Kapitel lesen Erstes Kapitel lesen

Application of Machine Learning Models in Agricultural and Meteorological Sciences

verfasst von: Mohammad Ehteram, Akram Seifi, Fatemeh Barzegari Banadkooki

Verlag: Springer Nature Singapore

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten
insite
SUCHEN

Über dieses Buch

This book is a comprehensive guide for agricultural and meteorological predictions. It presents advanced models for predicting target variables. The different details and conceptions in the modelling process are explained in this book. The models of the current book help better agriculture and irrigation management. The models of the current book are valuable for meteorological organizations.

Meteorological and agricultural variables can be accurately estimated with this book's advanced models. Modelers, researchers, farmers, students, and scholars can use the new optimization algorithms and evolutionary machine learning to better plan and manage agriculture fields. Water companies and universities can use this book to develop agricultural and meteorological sciences. The details of the modeling process are explained in this book for modelers.

Also this book introduces new and advanced models for predicting hydrological variables. Predicting hydrological variables help water resource planning and management. These models can monitor droughts to avoid water shortage. And this contents can be related to SDG6, clean water and sanitation.

The book explains how modelers use evolutionary algorithms to develop machine learning models. The book presents the uncertainty concept in the modeling process. New methods are presented for comparing machine learning models in this book. Models presented in this book can be applied in different fields. Effective strategies are presented for agricultural and water management. The models presented in the book can be applied worldwide and used in any region of the world. The models of the current books are new and advanced. Also, the new optimization algorithms of the current book can be used for solving different and complex problems. This book can be used as a comprehensive handbook in the agricultural and meteorological sciences. This book explains the different levels of the modeling process for scholars.

Inhaltsverzeichnis

Frontmatter
Chapter 1. The Importance of Agricultural and Meteorological Predictions Using Machine Learning Models
Abstract
This chapter reviews the applications of machine learning (ML) models for predicting meteorological and agricultural variables. The advantage and disadvantages of models are explained. This chapter also explains the importance of meteorological and agricultural predictions for water resource planning and management. The details of different machine learning models are explained. Afterward, the applications of these models are described. The ML includes different methods for learning predictive rules from historical datasets to predict unknown future data. Several studies have reported the superiority of ML techniques in agricultural and weather predictions that can maximize agricultural profit.
Mohammad Ehteram, Akram Seifi, Fatemeh Barzegari Banadkooki
Chapter 2. Structure of Particle Swarm Optimization (PSO)
Abstract
PSO is an evolutionary algorithm for solving the optimization problem. This chapter explains the mathematical model and structure of PSO. The PSO is initialized with random positions and the velocity of random particles. Then, it searches for the global optimum solution by adjusting each particle’s moving vector based on each particle’s personal (cognitive) and global (social) best positions at each iteration. Also, this chapter reviews the application of PSO in different fields. In summary, many climatic and agricultural studies have proposed applying the PSO as an appropriate approach for solving related problems.
Mohammad Ehteram, Akram Seifi, Fatemeh Barzegari Banadkooki
Chapter 3. Structure of Shark Optimization Algorithm
Abstract
This chapter studies the structure of the shark optimization algorithm (SSO). First, the applications of the shark algorithm are reviewed in different fields. The SSO can identify optimal solutions by balancing exploitation and exploration phases. The SSO benefits from low computation costs and fast convergence properties. The rotational movement of sharks is used to escape from the local optimums. It is suggested to explore SSO’s capability for many additional applications, such as crop planning, crop pattern optimization, irrigation water allocation, and crop yield.
Mohammad Ehteram, Akram Seifi, Fatemeh Barzegari Banadkooki
Chapter 4. Sunflower Optimization Algorithm
Abstract
This chapter explains the mathematical model and structure of sunflower optimization (SFO). The algorithm acts based on the life of the SFO. When the distance of a flower from the sun increases, the radiation intensity decreases. The sunflower seeks the best orientation toward the sun. The SFO has a high ability to solve optimization problems. The SFO can be easily implemented for solving complex problems. The SFO outperformed the other optimization algorithms, such as particle swarm optimization (PSO), genetic algorithm (GA), and other algorithms. The SFO can be used for solving complex problems in different fields. It also can be used for training soft computing models. The SFO can be coupled with other optimization algorithms for solving complex problems.
Mohammad Ehteram, Akram Seifi, Fatemeh Barzegari Banadkooki
Chapter 5. Henry Gas Solubility Optimizer
Abstract
This chapter explains the structure and mathematical model of the Henry gas solubility optimization (HGSO). Also, the different applications of HGSO are reviewed in other fields. The HGSO uses advanced operators for solving complex optimization problems. The HGSO can converge earlier than the other optimization algorithm. The HGSO had a high efficiency for solving multi-objective optimization problems. The HGSO also can be used for training soft computing models. The HGSO is a robust algorithm.
Mohammad Ehteram, Akram Seifi, Fatemeh Barzegari Banadkooki
Chapter 6. Structure of Crow Optimization Algorithm
Abstract
This chapter explained the structure and mathematical model of the crow optimization algorithm (COA). A characteristic of crows is hiding their food. COA’s mathematical model is defined based on the mechanism of hiding food. The algorithms can be used for solving complex problems such as the optimal operation of dam reservoirs, training soft computing models, optimal design of structures, and flood control. The COA can be easily implemented. The fast convergence is another advantage of COA. The COA has high efficiencies for solving multi-objective optimization problems. The COA can be easily coupled with different optimization algorithms.
Mohammad Ehteram, Akram Seifi, Fatemeh Barzegari Banadkooki
Chapter 7. Structure of Salp Swarm Algorithm
Abstract
This chapter explains the theory of the salp swarm algorithm (SSA). The SSA can be easily implemented. Also, adjusting SSA parameters is easy. The fast convergence and high accuracy are the advantages of SSA. The SSA can be coupled with optimization algorithms to solve complex problems. SSA is an example of a strong algorithm. This algorithm has few parameters. The best solution in the algorithm will guide the other solutions. The SSA can be coupled with soft computing models for finding their parameter values.
Mohammad Ehteram, Akram Seifi, Fatemeh Barzegari Banadkooki
Chapter 8. Structure of Dragonfly Optimization Algorithm
Abstract
This chapter explains the structure and mathematical model of the dragonfly optimization algorithm (DFOA). The dragonfly is regarded as a small predator in nature. However, during the exploration phase, dragonflies form small groups and fly back and forth to seek food and attract prey. The DFOA can be used for solving different optimization problems. The DFOA can be easily implemented. Also, the DFOA can be coupled with different optimization algorithms. The DFOA can be used for solving multiobjective optimization problems. The DFOA is a robust optimization algorithm for training soft computing models. This chapter indicated that the DFOA was successfully used in different fields.
Mohammad Ehteram, Akram Seifi, Fatemeh Barzegari Banadkooki
Chapter 9. Rat Swarm Optimization Algorithm
Abstract
This chapter reviews the application of rat swarm optimization algorithms (RSOA) for solving different optimization problems. RSOA is a robust and simple optimization algorithm. There are both male and female rats in a group of rats. A mathematical model of rats’ chasing and fighting behaviors is used to design an RSO algorithm and optimize the results. The results indicated that the RSOA was implemented for solving complex problems. The RSOA is a robust optimizer for training soft computing models. The high accuracy and fast convergence are the advantages of RSOA.
Mohammad Ehteram, Akram Seifi, Fatemeh Barzegari Banadkooki
Chapter 10. Antlion Optimization Algorithm
Abstract
Modelers may encounter multidimensional problems. Some of these problems may have constraints. Solving such problems requires robust models. This chapter explains the structure and mathematical model of the antlion optimization algorithm (ALO). Antlions dig holes in the sand. Their prey is trapped in holes. The ALO uses elitism to maintain the best solutions. The ALO can be applied to solve complex problems. The other optimization algorithms can be coupled with ALO to improve the quality of solutions. Also, the ALO can be used as a robust training algorithm for training soft computing models. The fast convergence and high accuracy are the advantages of ALO.
Mohammad Ehteram, Akram Seifi, Fatemeh Barzegari Banadkooki
Chapter 11. Predicting Evaporation Using Optimized Multilayer Perceptron
Abstract
In this study, the sunflower algorithm (SUA), shark algorithm (SHA), and particle swarm optimization (PASO) were integrated with the multilayer perceptron (MULP) model to predict daily evaporation. The average temperature (AVT), relative humidity (REH), wind speed (WISP), number of sunny hours (NSH), and rainfall (RAI) were used to predict evaporation at the Hormozgan, Fars, Mazandaran, Yazd, and Isfahan stations located in Iran country. The accuracy of the models indicated that the MULP-SUA provided the highest accuracy at the different stations. Also, the AVT and NSH were the most important parameters in desert climates. The results indicated that the optimized MULP models performed better than the MULP models.
Mohammad Ehteram, Akram Seifi, Fatemeh Barzegari Banadkooki
Chapter 12. Predicting Rainfall Using Inclusive Multiple Model and Radial Basis Function Neural Network
Abstract
This study used the salp swarm algorithm (SSA), Henry gas solubility optimization algorithm (HGSOA), and crow optimization algorithm (COA) to adjust the radial basis function neural network (RABFN) parameters for predicting monthly rainfall. Then, a new ensemble model was created using the outputs of RABFN, RABFN-SSA, RABFN-HGSOA, and RABFN-COA. The new ensemble model was named inclusive multiple model (IMM). This study indicated that the ensemble models improved the efficiency of the optimized RABFN models. The training MAE of the IMM, RABFN-HGSOA, RABFN-SSA, RABFN-PSO, and RBFN models was 0.987, 1.35, 1.47, 1.58, and 2.21 mm. The IMM reduced the testing MAE of the IMM, RABFN-HGSOA, RABFN-SSA, RABFN-PSO, and RBFN models by 32%, 37%, 42%, and 55%, respectively. Also, the HGSOA had better performance than the SSA and COA.
Mohammad Ehteram, Akram Seifi, Fatemeh Barzegari Banadkooki
Chapter 13. Predicting Temperature Using Optimized Adaptive Neuro-fuzzy Interface System and Bayesian Model Averaging
Abstract
This study uses an optimized adaptive neuro-fuzzy interface system (ANFIS) and Bayesian model averaging (BMA) to estimate one-month-ahead temperature. The lagged temperatures were used as the inputs to the models. The dragonfly optimization algorithm (DRA), rat swarm optimization (RSOA), and antlion optimization algorithm (ANO) were used to set the ANFIS parameters. The results indicated that the BMA model outperformed the other models. Also, the DRA had the best performance among other optimization algorithms. The Nash–Sutcliffe efficiency (NSE) of the BMA, ANFIS-DRA, ANFIS-RSOA, ANFIS-ANO, and ANFIS models was 0.96, 0.91, 0.90, 0.89, and 0.87, respectively. The BMA and ANFIS-DRA had the highest NSE values at the testing level. It was observed that increasing time horizons decreased the accuracy of models.
Mohammad Ehteram, Akram Seifi, Fatemeh Barzegari Banadkooki
Chapter 14. Predicting Evapotranspiration Using Support Vector Machine Model and Hybrid Gamma Test
Abstract
In agriculture and water resource management, evapotranspiration prediction plays an important role. In this article, the optimized SVM models are used for predicting evapotranspiration. In this study, the SVM parameters are adjusted using particle swarm optimization (PSO), antlion optimization (ANO), and crow optimization algorithm (COA). For choosing the best input combination, a hybrid gamma test is used. Automatically, the hybrid gamma test can determine the best input combination. The optimized SVM models outperformed the standalone SVM models. The mean absolute error (MAE) of the SVM-ANO, SM-COA, SVM-PSO, and SVM models was 0.678, 0.789, 0.812, and 0.824 at the Iranshahr station.
Mohammad Ehteram, Akram Seifi, Fatemeh Barzegari Banadkooki
Chapter 15. Predicting Infiltration Using Kernel Extreme Learning Machine Model Under Input and Parameter Uncertainty
Abstract
This study develops the optimized kernel extreme learning machines (KELMs) for predicting the infiltration rate. The rat swarm optimization algorithm (RSOA), shark optimization (SO), and dragonfly algorithm (DRA) were used to find the KELM parameters. This study also used generalized likelihood uncertainty estimation (GLUE) for quantifying input and parameter uncertainties. The furrow length had the highest importance among other input parameters. Also, the KELM-RSOA outperformed the other models. The MAE of the KELM-RSOA, KEML-SO, KELM-DRA, and KELM models was 0.02, 0.05, 0.07, and 0.10 at the training level. The MAE of the KELM-RSOA, KEML-SO, KELM-DRA, and KELM models was 0.04, 0.08, 0.10, and 0.12 at the testing level. The results revealed that the model parameters provided higher uncertainty than the input parameters.
Mohammad Ehteram, Akram Seifi, Fatemeh Barzegari Banadkooki
Chapter 16. Predicting Solar Radiation Using Optimized Generalized Regression Neural Network
Abstract
One of the most important components of the hydrological cycle is solar radiation. Three stations in Iran were used to predict monthly solar radiation (SOR) using the optimized generalized regression neural network (GRNN). The Henry gas solubility optimization (HGSO), antlion optimization (ANO), and salp swarm algorithm (SSA) were used to adjust the parameters of the GRNN. Sunny hours had the highest correlation with SOR at all stations. Furthermore, the GRNN-HGSO model outperformed the other methods. At Mazandaran station, the median of observed data, GRNN-HGSO, GRNN-ANO, GRNN-SSA, and GRNN model was 19 MJ m−2, 19 MJ m−2, 19 MJ m−2, 21 MJ m−2, and 24 MJ m−2, respectively. In this study, soft computing models had a high ability to predict SOR in different climates. Using the models of the current study, decision-makers can identify the regions with the highest SRO. These regions are suitable for the construction of power plants.
Mohammad Ehteram, Akram Seifi, Fatemeh Barzegari Banadkooki
Chapter 17. Predicting Wind Speed Using Optimized Long Short-Term Memory Neural Network
Abstract
Predicting wind speed is an important aspect of energy management. We used optimized long short-term memory (LSTM) to predict wind speed at different stations. LSTM parameters were adjusted using sunflower optimization (SUNO), crow optimization algorithm (COA), and particle swarm optimization (PSO). We used lagged wind speed values as inputs to the models. The best input combination was determined using the person correlation method. Based on the performance of the models, the optimized LSTM models outperformed the standalone models. This study can be useful if modelers cannot access all input data. The results also indicated that each optimization algorithm provided different accuracies depending on its advanced operators.
Mohammad Ehteram, Akram Seifi, Fatemeh Barzegari Banadkooki
Chapter 18. Predicting Dew Point Using Optimized Least Square Support Vector Machine Models
Abstract
Dew point prediction (DPT) is an important topic in agriculture and water resource management. In this chapter, robust soft computing models are used for estimating DPT. This study uses a standalone least square support vector machine (LSSVM) and LSSVM models to estimate the DPT. In this chapter, the LSSVM-antlion optimization algorithm (ANOA), LSSVM-dragonfly algorithm (DOA), LSSVM-crow optimization algorithm (LSSVM-COA), and LSSVM were used to estimate DPT. The different input combinations were used to predict DPT. The results indicated that the optimized LSSVM outperformed the LSSVM models. The best input variable consisted of input variables of relative humidity (RHU), average temperature (AVTEM), wind speed (WIPSE), and number of sunny hours (NOSH). The results indicated that the optimized LSSVM models outperformed the LSSVM models.
Mohammad Ehteram, Akram Seifi, Fatemeh Barzegari Banadkooki
Metadaten
Titel
Application of Machine Learning Models in Agricultural and Meteorological Sciences
verfasst von
Mohammad Ehteram
Akram Seifi
Fatemeh Barzegari Banadkooki
Copyright-Jahr
2023
Verlag
Springer Nature Singapore
Electronic ISBN
978-981-19-9733-4
Print ISBN
978-981-19-9732-7
DOI
https://doi.org/10.1007/978-981-19-9733-4