A new robust hybrid model based on support vector machine and firefly meta-heuristic algorithm to predict pistachio yields and select effective soil variables

Seyedmohammadi, Javad; Zeinadini, Ali; Navidi, Mir Naser; McDowell, R. W.

doi:10.1016/j.ecoinf.2023.102002

Cited by 23 publications

(11 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The selection of these attributes is a very important task for predicting yield, as highlighted in previous works. [18][19][20] Thus, some variants were selected for the study, such as pruning times, data collection year (2017, 2018, and 2017 + 2018), all chemical attributes of soil and leaf (called 'Leaf/Soil'), soil and leaf attributes that have the highest Pearson correlation with yield, S (leaf), MO (soil), S (soil), Zn (leaf), Ca (leaf), K (leaf), T (soil), P (leaf), B (soil) and C (soil); and, finally, only the chemical attributes of leaf with the highest Pearson correlation, namely: S (leaf), Zn (leaf), Ca (leaf), K (leaf), and P (leaf ).…”

Section: Discussionmentioning

confidence: 99%

“…These algorithms were also used in the literature, utilizing soil characteristics as attributes for model learning. [18][19][20] The use of the flowchart (Fig. 1) to predict the yield data of the studied crops was based on an analysis of the chemical attributes of the soil and leaves in two consecutive harvests.…”

Section: Data Analysis and Machine Learningmentioning

confidence: 99%

“…Aparecido et al 17 applied different models to predict diseases and pests in coffee plants. Seyedmohammadi et al 18 used regression tree, k-nearest neighbors, and support vector machines to predict yield and manage the use of natural resources sustainably in pistachio production. In another study, Eskandari et al 19 presented a methodology to estimate date production using soil characteristics and machine learning methods, multivariate regression, and artificial neural networks.…”

Section: Introductionmentioning

confidence: 99%

“…applied different models to predict diseases and pests in coffee plants. Seyedmohammadi et al 18 . used regression tree, k‐nearest neighbors, and support vector machines to predict yield and manage the use of natural resources sustainably in pistachio production.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Models for predicting coffee yield from chemical characteristics of soil and leaves using machine learning

de Oliveira Faria,

Filho,

Santana

et al. 2024

J Sci Food Agric

View full text Add to dashboard Cite

BackgroundCoffee farming constitutes a substantial economic resource. This crop represents a source of income for several countries due to the high consumption of coffee drinks worldwide. Precise management of coffee crops involves collecting crop attributes (soil, plant), mapping, and applying inputs according to the plant's needs. This differentiated management is Precision Coffee Growing stands out for its increased yield and sustainability.ResultsThus, this research aimed to predict yield in coffee plantations by applying machine learning methodologies to soil and plant attributes. The data was obtained in a field of 54.6ha during two consecutive seasons, applying varied fertilization rates according to recommendations of soil attributes maps. Furthermore, monitoring leaf analysis maps seeks to establish a correlation between input parameters and yield prediction. The machine learning models obtained from this data efficiently predicted coffee yield. The best model demonstrated predictive fit results of 0.86 Pearson correlation. Soil chemical attributes did not interfere with the prediction models, indicating that this analysis can be dispensed with when applying these models.ConclusionThese findings have important implications for optimizing coffee management and cultivation, providing valuable insights for producers and researchers interested in maximizing yield using precision agriculture.This article is protected by copyright. All rights reserved.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Data Analysis and Machine Learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Models for predicting coffee yield from chemical characteristics of soil and leaves using machine learning

de Oliveira Faria,

Filho,

Santana

et al. 2024

J Sci Food Agric

View full text Add to dashboard Cite

show abstract

“…Artificial neural network (ANN) and random forest (RF) algorithms were employed for estimation, resulting in relative root mean square error (RRMSE) values ranging from 7.9 to 14.5% for wall-to-wall prediction and 6.8-11.8% for projection. Seyedmohammadi et al (2023) aimed to predict yield and effectively manage natural resources in the study by modeling the impact of soil properties using various algorithms such as classification and regression tree, k-nearest neighbors, support vector machines, and a hybrid model combining support vector machines with the firefly meta-heuristic algorithm. Soil samples from 124 pistachio orchards in Iran were analyzed, and critical predictors were selected based on correlation coefficients, sensitivity analysis, and ANOVA hypothesis testing.…”

Section: Introductionmentioning

confidence: 99%

Quantifying effects of climate change and farmers' information demand on wheat yield in India: a deep learning approach with regional clustering

Godara,

Birthal,

Avinash

et al. 2024

Front. Sustain. Food Syst.

View full text Add to dashboard Cite

IntroductionWith increasing demand for food and changing environmental conditions, a better understanding of the factors impacting wheat yield is essential for ensuring food security and sustainable agriculture. By analyzing the effect of multiple factors on wheat yield, the presented research provides novel insights into the potential impacts of climate change on wheat production in India. In the present study, datasets consisting of countrywide environmental and agronomic factors and wheat yield were collected. In addition, the study also analyzes the effect of information demand of farmers on production.MethodologyThe study employs a regional analysis approach by dividing the country into five zonal clusters: Northern Hills, Central India, Indo-Gangetic Plains, North-Eastern India, and Peninsular India. Correlation and Principal Component Analysis (PCA) were performed to uncover the month-wise key factors affecting wheat yield in each zone. Furthermore, four Machine Learning/Deep Learning-based models, including XGBoost, Multi-layer Perceptron (MLP), Gated Recurrent Unit (GRU), and 1-D Convolutional Neural Network (CNN), were developed to estimate wheat yield. This study estimated partial derivatives for all factors using Newton's Quotient Technique, a numerical method-based approach.ResultsThe analysis focused on applying this technique to the best-performing wheat yield estimation model, which was the GRU-based model (with RMSE and MAE of 0.60 t/ha and 0.46 t/ha, respectively).DiscussionIn the later sections of the article, multiple policy recommendations are communicated based on the extracted insights. The results of the presented research help inform decision-making regarding the development of strategies and policies to mitigate the impacts of climate change on wheat production in India.

show abstract

Mapping China's reserved arable lands and its sustainable cropping layout

Chen,

He,

Wang

et al. 2024

J Sci Food Agric

View full text Add to dashboard Cite

BACKGROUNDReserved arable lands in China is of great significance for rationally allocating crop planting structures, alleviating the pressure of grain imports, and protecting food security. Owing to data acquisition limitations, obtaining the spatial distribution of reserved arable lands at large spatial scales is relatively rare, and there is little information on predicting the suitability, production capacity, and ecological effects of crop cultivation in reserved arable lands. This study obtained the distribution of reserved arable lands in China by applying restrictive factors, and used the Food and Agriculture Organisation of the United Nations (FAO) suitability index for eight crops to obtain a spatial distribution map of suitable crops, proposed a cropland ecological efficiency index (CEEI) to analyse the ecological impact of crop cultivation in reserved arable lands.RESULTSChina possesses approximately 3.93 million hectares of viable reserved arable lands comprising primarily grasslands (67.68%), sandy land (8.11%), saline‐alkali land (20.68%), and bare land (3.53%). The average CEEI for the eight crops under irrigation conditions ranges from 0.844 to 0.865, and that under rain‐fed conditions (excluding rice) ranges from 0.609 to 0.779.CONCLUSIONWe proposed the development of rain‐fed agriculture with sorghum as the primary crop in the central part of Shanxi and Inner Mongolia, while promoting the cultivation of rapeseed and soybeans in the eastern parts of Heilongjiang, Jilin, and Inner Mongolia. Overall, the development of irrigation agriculture focusing on wheat and barley should be pursued only when water resources are guaranteed, particularly in north‐western regions such as Gansu, Ningxia, Xinjiang, Qinghai, and Shaanxi. © 2024 Society of Chemical Industry.

show abstract

A new robust hybrid model based on support vector machine and firefly meta-heuristic algorithm to predict pistachio yields and select effective soil variables

Cited by 23 publications

References 48 publications

Models for predicting coffee yield from chemical characteristics of soil and leaves using machine learning

Models for predicting coffee yield from chemical characteristics of soil and leaves using machine learning

Quantifying effects of climate change and farmers' information demand on wheat yield in India: a deep learning approach with regional clustering

Mapping China's reserved arable lands and its sustainable cropping layout

Contact Info

Product

Resources

About