Agricultural Energy Consumption Research Articles

How does output price risk influence agricultural energy consumption? Evidence from China’s lychee market

ABSTRACT Agricultural price risk plays a critical role in shaping farmer behaviours. However, existing studies offer little evidence of how output price risk influences energy-related behaviours in agricultural production. In this study, we investigate the impact of output price risk on agricultural energy consumption by leveraging nationally representative data of lychee farmers with daily prices across the supply chain in China. Our findings robustly demonstrate that an increase in output price risk positively affects agricultural households’ energy expenditures. Additionally, we find that the effects of output price risk are more salient among samples of diesel consumption, small-scale households, and less-educated households. Furthermore, the mechanism analysis documents that output price risk significantly increases the likelihood of participating in the non-farm occupation, as well as adopting energy-powered production technologies and productive fixed assets.

The Impact of Agriculture on the Consumption of Natural Resources (An analytical study)

This research delves into the multifaceted relationship between agriculture and the consumption of natural resources, highlighting the significant impact of agricultural practices on natural resource depletion. Various studies have explored this dynamic, revealing how technological advancements, government policies, and market access in developed countries have contributed to the increased consumption of natural resources in agriculture. The expansion of palm oil plantations in Indonesia, for instance, has raised concerns about land scarcity and environmental degradation due to soil compaction and water retention issues. Conversely, research in the U.S. suggests that the availability of natural resources, except in cases of major energy supply interruptions, does not significantly constrain agricultural output. The study also examines the role of energy consumption in agriculture, with findings indicating that an increase in gas consumption boosts GDP, whereas higher electricity consumption may hinder growth. Additionally, the research addresses the effects of natural disasters on agriculture, food security, and natural resources, with typhoons notably impacting rice production and household food security in the Philippines. Through a critical and analytical lens, this paper aims to provide a comprehensive understanding of how agricultural practices influence the depletion of natural resources and explore potential strategies for mitigating these effects. Given the study's outcomes, several policy recommendations emerge as follow: Governments should create incentives for the adoption of renewable energy technologies in agriculture to reduce reliance on non-renewable resources, There is a need for comprehensive water management policies that ensure more sustainable water use in agriculture.

Environmental impact assessment of horse and mechanical traction for vineyard cultivation

In the European Union, energy consumption in agriculture and forestry is less intense than in other economic sectors. However, fossil and non-renewable sources, particularly oil, are predominant, with higher percentages than in different economic sectors. In this context, this study aims to compare the environmental impact generated by equine and mechanical traction for viticulture practices in an organic production context, using life cycle assessment (LCA). Three scenarios were considered: business as usual (i.e., tractor-grown grapes) and horse-grown grapes but with two feeding options (tractor-grown hay and horse-grown hay). The results show that the tractor-grown grape scenario has higher impacts in five impact categories whereas the horse-grown scenario shows higher Global Warming, and to a minor extent Land use. Specifically, the worst results of the control scenario are in the mid-point category of Inorganic Respiratory due to fuel use, which produces P M 2.5. Fuel use is also the cause of the highest environmental burdens in other categories such as terrestrial Ecotoxicity. A sensitive analysis of the results was performed considering the endpoint damage categories. The outcomes show that, in general, the impact of horses is quite stable even under potentially different conditions. Some categories (ecosystem quality, global impact) are only slightly affected by variation in growth time, while all other categories (human health, resources, climate change) experience greater variation.

Evolution and driving factors of inequality in CO2 emissions from agricultural energy consumption in China

The inequality in CO2 emissions from agricultural energy consumption is a major challenge for coordinating low-carbon agricultural development across regions in China. However, the evolutionary characteristics and driving factors of inequality in China’s agricultural energy-related CO2 emissions are poorly understood. In response, the Kaya–Theil model was adopted to examine the three potential factors influencing CO2 emission inequality in China’s agricultural energy consumption. The results revealed that, from 1997 to 2021, agricultural energy-related CO2 emissions per capita showed a significant upward trend, with prominent polarization and right-tailing phenomena. Overall, the inequality was on a downward trend, with the Theil index falling from 0.4109 in 1997 to 0.1957 in 2021. Meanwhile, the decomposition of the national inequality revealed that the within-group inequality declined from 0.3991 to 0.1634, which was greater than between-group inequality, based on zoning the 28 provinces into three grain production functional areas. As for the three kaya factors, the energy intensity contributed the most to the overall inequality, followed by the agricultural economic development and CO2 emission intensity. Based on these results, this study provided some potential strategies to reduce agricultural-related CO2 emissions.

A globalized methodology of energy-saving solar greenhouse design in high latitudes

The energy-saving solar greenhouse (ESSG) represents a Chinese-type agricultural building of facilitating low-energy and zero-carbon vegetable overwintering production in high latitudes and cold regions. However, its application benefit outside of China has been limited. To establish an operational ESSG design scheme applicable worldwide, this study developed a comprehensive methodology and specific parameters for different latitudinal regions. The ESSG design was determined based on considerations of daylighting, thermal insulation, heat storage-release capacity, and structural safety. Through validation in six representative regions, the reliability of the ESSG design methodology was confirmed. The optimal design values for front roof angle, ridge height, and back wall height were identified across different latitudes. ESSG in various latitudinal regions from 32°N to 48°N exhibited annual cumulative temperatures could reach 8 × 103∼1.3 × 104°C and accumulated light interception could reach 2 × 1012∼4 × 1012J. Even in the 48°N region, the average internal temperature of the greenhouse exceeded 8 °C, with a nighttime cooling rate lower than 0.75 °C/h and a maximum temperature difference between internal and external environments exceeding 40 °C. This suggests the ESSG fully meets the non-heated overwintering production requirements for common vegetables. The research findings provide crucial theoretical foundations for the global promotion of ESSG, contributing to the reduction of energy consumption and carbon emissions in the sustainable agriculture.

Experimental study of ambient temperature and humidity distribution in large multi-span greenhouse based on different crop heights and ventilation conditions

Analyzing the distribution of temperature and humidity within a greenhouse is essential for optimizing ventilation strategies and improving crop quality and yield. The temperature and humidity distribution of eight-span greenhouse under natural ventilation and mechanical ventilation is studied experimentally. The influence of different crop height on temperature and humidity distribution in greenhouse and the influence of different mechanical ventilation strategies on temperature regulation were discussed. The results showed that the temperature difference between inside and outside the greenhouse decreased with the increase of crop height. Under natural ventilation conditions, the soil surface temperature is the highest, and the temperature at 0.5 m above the surface is the lowest, with the maximum temperature difference of 0.9 ℃. The temperature in the greenhouse was higher in the west and lower in the east, and the temperature difference decreased with the increase of crop height. In the east–west direction, the maximum temperature difference between tall crops, short crops and non-planted crops was 0.7 ℃, 0.9 ℃ and 1.0 ℃, respectively. High crops increase the relative humidity in the greenhouse and increase the uneven distribution of relative humidity. When growing tall crops, the difference between indoor and outdoor relative humidity is only 2.3 %. When the external shade and fan are turned on at the same time, the cooling effect is the best, the energy consumption is lower, and the temperature distribution is the most uniform. The results provide a valuable reference for optimizing greenhouse structure, formulating ventilation strategy and reducing agricultural energy consumption.

A Study on the Influence Factors of Agricultural Carbon Emissions in Hunan Province Based on Random Forest Model

Agricultural carbon reduction contributes to the realization of “carbon peak and carbon neutrality” strategy. This article analyzes the previous years’ data of agricultural carbon emissions in Hunan Province, and obtains the variation of carbon emissions; Using the random forest method to analyze the influence factors of agricultural carbon emissions in Hunan Province, it is proven that unit crop production value, unit energy carbon emissions in agriculture, and unit agricultural GDP energy consumption are the three most critical factors affecting agricultural carbon emissions in Hunan Province. LDMI method is used for validation. Sensitivity analysis was conducted on factors such as agricultural energy consumption, total production value of AFAF(Agriculture, forestry, animal husbandry, and fishing), total agricultural production value, crop yield, crop planting area, and non-urban population. The first five changes have a positive impact on agricultural carbon emissions, while non-urban population has a downward and then upward trend.

The rebound effect of energy consumption and its determinants in China's agricultural production

With the facilitation of agricultural modernization, China's agricultural energy consumption continues to rise. This paper empirically tests the agricultural energy rebound effect and its influencing factors in China during 1999–2020. It is believed that the improvement of energy efficiency has not led to the expected energy-saving effect in agriculture due to the "Jevons paradox" of energy efficiency and energy consumption. The average energy efficiency of China's agricultural energy consumption was 0.446, and the average energy rebound effect was 68.9 %. The level of agricultural mechanization, the effective irrigated area of farmland and agricultural investment have a positive impact on the rebound effect of agricultural energy, and the direct effects are 0.062, 0.008 and 0.064, respectively, while agricultural labor force and energy price have a negative impact on the rebound effect of agricultural energy. In particular, technology spillover and scale spillover led by agricultural technology progress have strong negative space spillover effect. As it is argued, 1 % of agricultural technology progress can reduce 3.5 % of agricultural energy rebound effect in surrounding areas. In order to reduce the energy rebound effect, it is suggested to increase the subsidies to agricultural labors and rationally formulate regional differentiated energy regulation policies.

Prediction model and demonstration of regional agricultural carbon emissions based on Isomap–ACO–ET: a case study of Guangdong Province, China

Scientific analysis of regional agricultural carbon emission prediction models and empirical studies are of great practical significance to the realization of low-carbon agriculture, which can help revitalize and build up ecological and beautiful countryside in China. This paper takes agriculture in Guangdong Province, China, as the research object, and uses the extended STIPAT model to construct an indicator system for the factors influencing agricultural carbon emissions in Guangdong. Based on this system, a combined Isomap–ACO–ET prediction model combing the isometric mapping algorithm (Isomap), ant colony algorithm (ACO) and extreme random tree algorithm (ET) was used to predict agriculture carbon emissions in Guangdong Province under five scenarios. Effective predictions can be made for agricultural carbon emissions in Guangdong Province, which are expected to fluctuate between 11,142,200 tons and 11,386,000 tons in 2030. And compared with other machine learning and neural network models, the Isomap–ACO–ET model has a better prediction performance with an MSE of 0.00018 and an accuracy of 98.7%. To develop low-carbon agriculture in Guangdong Province, we should improve farming methods, reduce the intensity of agrochemical application, strengthen the development and promotion of agricultural energy-saving and emission reduction technologies and low-carbon energy sources, reduce the intensity of carbon emissions from agricultural energy consumption, optimize the agricultural planting structure, and develop green agricultural products and agro-ecological tourism according to local conditions. This will promote the development of agriculture in Guangdong Province in a green and sustainable direction.

Reducing energy consumption without compromising food security: the imperative that could transform agriculture

Abstract The imperative of carbon neutrality requires a drastic, rapid, and sustained reduction in fossil energy consumption and greenhouse gas emissions. The Russia-Ukraine war has led to a major energy crisis, whose end does not seem imminent. The sudden and major increase in energy prices resulting from this crisis has major impacts on many sectors of the societies. This is especially true for agriculture, a direct consumer of energy that also has considerable indirect consumption through the manufacture, transport, and distribution of chemical inputs such as fertilizers and pesticides. Taking the example of France, from July 2021 to July 2022, farmers were challenged with price increases as high as 48% and 111% for energy and fertilizers, respectively (Agreste, 2022). At the global scale, in 2018, greenhouse gas emissions from fossil energy consumption in agriculture represented 0.9 Pg CO2 eq. (against 9.3 Pg CO2 eq. due to agriculture, excluding emissions due to this energy consumption) and those emissions have increased by 23% since 2000 (FAO, 2020). 
This context calls for in-depth transformation of agriculture, which is currently overly dependent on non-renewable energy in high-income economies. While research on the subject continues to grow (Box 1), this large body of work focuses more on assessing the energy consumption of current agricultural systems using multiple metrics (Box 2) than on developing supply- or demand-side alternatives that use less energy. In response to these trends, Ramankutty and Dowlatabadi (2021) suggested pathways to sustainable food systems. However, while their recommendations included energy reduction options on the food consumption side, their focus on farming practices was restricted to improving the energy efficiency of current agricultural systems and missed the necessary redesign of farming and food systems.
In this article, we look back to understand how agricultural systems came to progressively depend on non-renewable energy. We then briefly review agricultural practices and systems reducing energy consumption without compromising energy efficiency. Finally, we propose future research avenues to explore pathways for reducing energy consumption without compromising food security and sustainability challenges.

Strategies of Climate Change Mitigation in Agriculture Plant Production—A Critical Review

Agriculture is the second-highest, after energy use, source of greenhouse gas emissions, which are released from soils and animal digestion processes and as a result of energy consumption at various stages of agricultural production. However, changes in the management of agricultural systems may mitigate the negative impact of this sector on the atmosphere and climate. This paper presents a literature review on energy consumption in agriculture and the potential of agricultural crop production to assist in mitigation of global warming by increasing absorption of CO2 from the atmosphere. The issue was considered in the context of managing the cultivation of main, catch and cover crops. The potential of carbon sequestration in the above- and below-ground biomass of selected crops was analyzed. It was stated that, depending on the species, main crops can sequester up to 113 CO2 ha−1 yr−1 in whole biomass, while catch or cover crops can sequester up to 14.80 CO2 ha−1 yr−1 and 0.17 CO2 ha−1 yr−1 in the above- and below-ground biomass, respectively. The benefits of the spread of catch or cover crops, such as improvement of soil quality (leading to an increase in primary crop yield by even as much as 65%) and a phytosanitary effect, as well as the barriers that limit the use of catch crops, including the problems with matching crop species to climate and soil conditions and the risk of reducing farmers’ income, were considered. The results of the review show that catch crops can assimilate an additional amount of 4 to 6 tonnes CO2 ha−1 yr−1, and thus, spreading of catch crops is an effective way to reduce the climate impact of agriculture.

Energy Consumption in Agricultural of Turkey

In this study, sectoral energy consumption and the share of sectors in total energy consumption in Turkey between the years 2017-2021 were examined. While the amount of energy consumed in the agricultural sector in Turkey was 4227 thousand TOE in 2017, it reached 5029 thousand TOE in 2021. The increase in energy consumption in agriculture occurred irregularly in the 5-year period specified. While the increase in energy consumption in agriculture was 8.37% in 2018 compared to the previous year, it was 2.85% in 2019 and 3.03% in 2021. In Turkey, the increase in energy consumption in agriculture in the period between 2017 and 2021 was calculated as 4.98%. In the specified period, the share of the industrial sector in total energy consumption was 32.30% on average, while the share of the agricultural sector was 4.16%.

Adoption of Renewable Energy Technology on Farms for Sustainable and Efficient Production: Exploring the Role of Entrepreneurial Orientation, Farmer Perception and Government Policies

Traditional energy consumption raises greenhouse gas emissions, which is a major concern in China. Agricultural energy consumption accounts for one third of China’s greenhouse gas emissions. Thus, current patterns of energy consumption on farms are both unsustainable and inadequate since rural communities in emerging nations have limited access to energy sources. This study explores the factors affecting the adoption of renewable energy on farms and examines the effect of such adoption on technical efficiency. The data were collected from 801 farmers selected through a multistage random and purposive sampling method in a face-to-face survey in China. Logistic regression, data envelopment analysis and propensity score matching were used to analyze the data. The descriptive statistics depicted that renewable energy technology was adopted by more than 25% of the total farmers. The logistic regression results depicted that education, farm size, government financial support, perceptions of renewable energy (usefulness, cost effectiveness, environmental friendliness and information availability) and farmer entrepreneurial orientation dimensions (risk-taking, innovativeness and pro-activeness) all significantly affected the adoption of renewable energy technology on farms. Farmers who perceived renewable energy as more useful and cost-effective than conventional energy technology were 1.89 and 2.13 times more likely to adopt it on their farms, respectively. Farmers who perceived renewable energy as more environmentally friendly than traditional energy technology were 1.54 times more likely to use it on their farms. The findings also showed that innovative farmers were 2.24 times more likely to adopt renewable energy technology on their farms. The propensity score matching results showed that the technical efficiency of adopters of renewable energy was 10% higher than that of nonadopters. The study suggests that agriculture must be transformed to fulfill the existing and forthcoming demand for food and energy in an impartial and ecologically sustainable manner.

Decomposing the decoupling relationship between energy consumption and economic growth in China's agricultural sector

Sustainable food supply is affected by high energy consumption and negative environmental effects. Regarding the national strategy of “carbon peaking and carbon neutrality targets”, the decoupling between energy consumption and economic growth in China's agriculture has received significant attention. Therefore, this study first presents a descriptive analysis of the energy consumption in China's agricultural sector from 2000 to 2019, before analyzing the decoupling state between energy consumption and agricultural economic growth at the national and provincial levels using the Tapio decoupling index. Finally, the logarithmic mean divisia index method is used to decompose the decoupling driving factors. The study draws the following conclusions: (1) At the national level, the decoupling of agricultural energy consumption from economic growth fluctuates among expansive negative decoupling, expansive coupling, and weak decoupling, before stabilizing in the last state. (2) The decoupling process also differs by geographic region. Strong negative decoupling is found in North and East China, and strong decoupling lasts longer in Southwest and Northwest China. (3) The factors driving decoupling are similar at both the levels. The economic activity effect promotes the decoupling of energy consumption. The industrial structure and energy intensity effects are the two main suppressive factors, whereas the population and energy structure effects have relatively weaker impacts. Therefore, based on the empirical results, this study provides evidence for regional governments to formulate policies on the relationship between the agricultural economy and energy management from the perspective of effect driven policies.

Engineering Design, Kinematic and Dynamic Analysis of High Lugs Rigid Driving Wheel, a Traction Device for Conventional Agricultural Wheeled Tractors

Traction failure on loose terrain is common in conventional agricultural wheeled tractors due to poor traction ability and lower power transfer efficiency of drive wheels, which leads to excessive energy consumption and soil compaction in agriculture. To overcome the problem, this paper presents a new design of a rigid lugged wheel for use in field tillage operations. This wheel was designed according to field operational requirements and also provided with rubber pads for smooth on-road drives. Kinematic and dynamic analysis of new wheel designs were carried out to study how they move, how they interact with the soil, and how they generate drive force in loose terrain soil. The relationship of wheel lug motion trajectories, displacement, and velocity of the wheel relative to field conditions, different travel reduction rates, and lug penetration/wheel sinkage were analyzed. Wheel-terrain interaction and shear stress-shear displacement relationships when the wheel is driven in soft, deformable terrain were studied using classic soil mechanics principles. It is found that the component of thrust in the direction of driving, i.e., driving force, is ranged between 81.52% and 86.17%, while the vertical component is reported to be less than 30% and further decreases to 9%, which is the compaction avoiding factor. The relationships, thus developed, of wheel parameters, soil stress and thrust characteristics, and wheel drive force were derived and revealed that the traction performance, power transfer efficiency, and trafficability of tractors in loose terrain can be improved by using the newly proposed wheel. A finite element method was used to analyze the designed wheel model for structural stability and optimization. The theoretical analysis results of the new drive wheel are convincing, so further tests and field operation research are recommended for sustainable adoption.

The impact of irrigation modes on agricultural water-energy‑carbon nexus

Despite the tremendous contribution of irrigated agriculture in addressing global food security, there is still confusion for farmers and governments about the choice of irrigation mode owing to the drastic environmental impacts of irrigation, including water shortage, energy crisis, and global warming. Exploring the agricultural water-energy‑carbon (WEC) nexus under different irrigation modes helps to accomplish the multi-objective of water & energy saving and carbon emission reduction. In this paper, a conceptual framework was nominated to evaluate the water & energy consumption and carbon emissions for winter wheat irrigation at township level and quantitatively discuss the complex interaction by the coupling coordination degree (CCD) of the WEC system under different irrigation modes in Henan Province, China. We discovered that irrigation modes profoundly affect water and energy consumption and carbon emissions in agriculture, as well as the spatial distribution of CCD from WEC system. Townships under irrigation mode with diversion and irrigation projects as the primary method (WDI) clustered together in the north and east with highest water consumption and carbon emissions, while townships under irrigation mode with rain-fed agriculture as the primary method (PI) accumulated in the west and south with lower water consumption and carbon emissions. Meanwhile, the CCD of the WEC nexus system was in basic coordination (0.40) and showed an unbalanced spatial distribution pattern with high in the southeast and low in the northwest. By comparing four irrigation modes, the coupling level of the WEC nexus system under irrigation mode with groundwater irrigation as the primary method (GI) was better and PI mode was the least ideal. This study helps to further understand agricultural WEC nexus under different irrigation modes and provide references for local governments in selecting appropriate irrigation modes to realize water-energy saving and carbon emission reduction in agricultural activities.

Comparative Energy Consumption Structure and Mode between China and Major Energy-Consuming Countries Under the Background of Carbon Emission Reduction

The top 23 countries with energy consumption accounting for 80% of the worldwide total in 2020 were selected as the research objects for this study. The energy consumption structure of these countries has been compared and studied from the proportion of clean energy in primary energy, the clean utilization rate of fossil energy, and the proportion of electric energy in terminal energy consumption, and the characteristics of energy consumption intensity were also analyzed based on the energy consumption per unit GDP, capital, and unit land area. The energy consumption patterns of various countries in social-economic operation, production, and life were also discussed, combined with the characteristics of industrial structure and subsector energy consumption. The concept of natural carbon sink load ratio of energy consumption was put forward, and the advantages and challenges of energy consumption mode transformation under carbon peak and carbon neutralization goals in China were identified and analyzed. The results showed that:the proportion of clean energy in primary energy, the proportion of energy consumption for power generation, the clean utilization rate of fossil energy, and the proportion of electric energy in terminal energy consumption in China were 15.90%, 53.48%, 37.51%, and 26.54%,respectively,all of which were in the forefront among the major energy-consuming countries in the world. China has built a favorable structural foundation for energy-intensive and clean utilization and formed a green and low-carbon energy consumption model; the proportion of non-industrial and agricultural energy consumption, especially that of transportation energy consumption, were both the lowest among major energy-consuming countries, and there is still much room for improvement in overall energy productivity based on the optimization of industrial structure. However, the relatively short carbon peak and neutralization target period poses a great challenge to the development speed and scale of clean energy to China, and the international situation under the constraint of carbon emission also increases the difficulty for China to achieve the carbon reduction goal by optimizing and adjusting the industrial structure.

A Crop Growth Prediction Model Using Energy Data Based on Machine Learning in Smart Farms.

In the recent past, the agricultural industry has rapidly digitalized in the form of smart farms through the broad usage of data analysis and artificial intelligence. Commonly, high operating costs in a smart farm are primarily due to inefficient energy usage. Therefore, accurate estimation of agricultural energy usage and environmental factors is considered as one of the significant tasks for crop growth control. The growth sequences of crops in agricultural environments like smart farms are related to agricultural energy usage and consumption. This study aims to develop and validate an algorithm that can interpret the crop growth rate response to environmental and solar energy factors based on machine learning, and to evaluate the algorithm's accuracy compared to the base model. The proposed model was determined through a comparative experiment of three representative machine learning techniques, which are random forest (RF), support vector machine (SVM), and gradient boosting machine (GBM), considering the energy usage for environmental control is highly associated with the paprika crop growth. Through the experiment performance with real data gathered from a paprika smart farm in South Korea, the multi-level RF can effectively predict paprika growth with an accuracy of 0.88, considering data analysis of factors that use solar energy. As a result of the experiment with the suggested model, the growth factors such as leaf length, leaf width, and environmental factors were found. Furthermore, the proposed algorithm can contribute to the development of applications through analysis of the crop growth big data for various plants in agricultural environments such as a smart farm.

Evaluating the impacts of technological progress on agricultural energy consumption and carbon emissions based on multi-scenario analysis.

Analyzing the impacts of technological progress on agricultural energy consumption and carbon emissions is of great significance for the development of low-carbon agriculture. Most of the existing studies focus on the agricultural sector level and lack of assessment of the impacts of technological progress on agricultural energy use and carbon emissions from the perspective of crops. In this study, we evaluated the impacts of technological progress on the energy consumption and carbon emissions of main crops in China under energy intensity constraints using a price endogenous partial equilibrium model with scenario analysis. We found that China's agriculture will have the highest yield and social welfare in 2025 under the production technological progress scenario, which will be 695.44 million t and 287.91 million yuan. Energy consumption for production will be the least under the energy technology progress scenario, which will be reduced by 9.02 million t ce or 16.01% compared to the baseline scenario. Under energy intensity constraints, synergy progress in production and energy technology will be the most effective way to reduce carbon emissions in the agricultural sector. Compared to the baseline, China's agricultural sector will reduce carbon emissions by 22.18 million t c in 2025 under the synergy scenario, a decrease of 16.18%. Therefore, we suggested that China's agricultural sector should pay more attention to the synergetic development of agricultural energy and production technology to further reduce carbon emissions and promote the development of green agriculture.

Renewable energy-powered semi-closed greenhouse for sustainable crop production using model predictive control and machine learning for energy management

Renewable energy consumption in agriculture is ascending, catering to the food needs of the rising population and protecting the environment. Maximizing renewable energy usage efficiency is essential for achieving sustainable development goals. In this work, a nonlinear integrated controlled environment agriculture model is constructed to correlate the impact of weather disturbances, temperature control actuators, humidity control actuators, fertilization, and irrigation to the states of crop production facilities and crop growing conditions. Linearization of the model is performed to reduce the computation time while retaining the accuracy of the nonlinear model. A robust model predictive control framework is developed to maximize renewable energy power usage efficiency and maintain a hospitable sustainable cultivation environment. To improve the robustness of control to hedge against the forecast uncertainties, the disjunctive data-driven uncertainty sets built upon the historical forecast errors are constructed by using machine learning methods, including principal component analysis and kernel density estimation. This work also presents the result of the simulation of controlling a renewable energy-powered semi-closed greenhouse growing tomatoes located in Ithaca, New York. Compared to other model predictive control frameworks, which do not leverage the machine learning approaches, the proposed control framework enables a 0.7%–66.9% reduction in renewable energy usage and a 0.7 wt% to 16.1 wt% increase in crop production. Further analysis of this work reveals that the integrated controlled environment agriculture model can help in increasing renewable energy usage efficiency from 4.7% to 127.5%.