Projecting life-cycle environmental impacts of corn production in the U.S. Midwest under future climate scenarios using a machine learning approach

Decision tree-based approach to extrapolate life cycle inventory data of manufacturing processes

Life cycle assessment (LCA) plays a crucial role in green manufacturing to uncover the critical aspects for alleviating the environmental burdens due to manufacturing processes. However, the scarcity of life cycle inventory (LCI) data for the manufacturing processes is a considerable challenge. This paper proposes a novel approach to extrapolate LCI data of manufacturing processes. Taking advantage of LCI data in the Ecoinvent datasets, decision tree-based supervised machine learning models, namely decision tree, random forest, gradient boosting, and adaptive boosting, have been developed to extrapolate the data of GHG emissions, i.e., carbon dioxide, nitrous oxide, methane, and water vapor. Initially, a correlation analysis was conducted to derive the most influential factors on GHG quantities resulting from manufacturing activities. First, the collected data have been preprocessed and split into train and test sets (70% and 30%, respectively). Second, a five-fold cross-validation method was applied to tune the hyperparameters of the models. Then, the models were re-trained using the best hyperparameters and evaluated using the test set. The results reveal that the Gradient Boosting model has a superior predictive performance for extrapolating the GHG emission data, with average coefficients of determination (R2) on the test set <0.95. Moreover, the model predictions involve relatively low values of the average root mean squared error and an average mean percentage of error on the test set. The correlation and feature importance analyses emphasized that the workpiece material and manufacturing technology have a considerable effect on natural resource consumption, i.e., energy, material, and water inflows into the process. Meanwhile, energy consumption, water usage, and raw aluminum depletion were the most influential factors in GHG emissions. Eventually, a case study to extrapolate the inflows and the outflows for new manufacturing activities has been conducted using the validated models. The proposed GraBoost model provides a computational supplementary approach to estimate and extrapolate the GHG emissions for different manufacturing processes when LCI data are incomplete or don't exist within LCI databases.

Predicting environmental impacts of smallholder wheat production by coupling life cycle assessment and machine learning

Wheat grain production is a vital component of the food supply produced by smallholder farms but faces significant threats from climate change. This study evaluated eight environmental impacts of wheat production using life cycle assessment based on survey data from 274 households, then built random forest models with 21 input features to contrast the environmental responses of different farming practices across three shared socioeconomic pathways (SSPs), spanning from 2024 to 2100. The results indicate significant environmental repercussions. Compared to the baseline period of 2018-2020, a similar upward trend in environmental impacts is observed, showing an average annual growth rate of 5.88 % (ranging from 0.45 to 18.56 %) under the sustainable pathway (SSP119) scenario; 5.90 % (ranging from 1.00 to 18.15 %) for the intermediate development pathway (SSP245); and 6.22 % (ranging from 1.16 to 17.74 %) under the rapid economic development pathway (SSP585). Variation in rainfall is identified as the primary driving factor of the increased environmental impacts, whereas its relationship with rising temperatures is not significant. The results suggest adopting farming practices as a vital strategy for smallholder farms to mitigate climate change impacts. Emphasizing appropriate fertilizer application and straw recycling can significantly reduce the environmental footprint of wheat production. Standardized fertilization could reduce the environmental impact index by 11.10 to 47.83 %, while straw recycling might decrease respiratory inorganics and photochemical oxidant formation potential by over 40 %. Combined, these approaches could lower the impact index by 12.31 to 63.38 %. The findings highlight the importance of adopting enhanced farming practices within smallholder farming systems in the context of climate change. SPOTLIGHTS.

A review of machine learning applications in life cycle assessment studies

Life Cycle Assessment (LCA) is a foundational method for quantitative assessment of sustainability. Increasing data availability and rapid development of machine learning (ML) approaches offer new opportunities to advance LCA. Here, we review current progress and knowledge gaps in applying ML techniques to support LCA, and identify future research directions for LCAs to better harness the power of ML. This review analyzes forty studies reporting quantitative assessment with a combination of LCA and ML methods. We found that ML approaches have been used for generating life cycle inventories, computing characterization factors, estimating life cycle impacts, and supporting life cycle interpretation. Most of the reviewed studies employed a single ML method, with artificial neural networks (ANNs) as the most frequently applied approach. Both supervised and unsupervised ML techniques were used in LCA studies. For studies using supervised ML, training datasets were derived from diverse sources, such as literature, lab experiments, existing databases, and model simulations. Over 70 % of these reviewed studies trained ML models with less than 1500 sample datasets. Although these reviewed studies showed that ML approaches help improve prediction accuracy, pattern discovery and computational efficiency, multiple areas deserve further research. First, continuous data collection and compilation is needed to support more reliable ML and LCA modeling. Second, future studies should report sufficient details regarding the selection criteria for ML models and present model uncertainty analysis. Third, incorporating deep learning models into LCA holds promise to further improve life cycle inventory and impact assessment. Finally, the complexity of current environmental challenges calls for interdisciplinary collaborative research to achieve deep integration of ML into LCA to support sustainable development.

Prospective life cycle assessment of viticulture under climate change scenarios, application on two case studies in France

Viticulture needs to satisfy consumers' demands for environmentally sound grape and wine production while envisaging adaptation options to diminish the impacts of projected climate change on future productivity. However, the impact of climate change and the adoption of adaptation levers on the environmental impacts of future viticulture have not been assessed. This study evaluates the environmental performance of grape production in two French vineyards, one located in the Loire Valley and another in Languedoc-Roussillon, under two climate change scenarios. First, the effect of climate-induced yield change on the environmental impacts of future viticulture was assessed based on grape yield and climate data sets. Second, besides the climate-induced yield change, this study accounted for the impacts of extreme weather events on grape yield and the implementation of adaptation levers based on the future probability and potential yield loss due to extreme events. The life cycle assessment (LCA) results associated with climate-induced yield change led to opposite conclusions for the two vineyards of the case study. While the carbon footprint of the vineyard from Languedoc-Roussillon is projected to increase by 29 % by the end of the century under the high emissions scenario (SSP5-8.5), the corresponding footprint is projected to decrease in the vineyard from the Loire Valley by approximately 10 %. However, when including the effect of extreme events and adaptation options, the life cycle environmental impacts of grape production are projected to drastically increase for both vineyards. For instance, under the SSP5-8.5 scenario, the carbon footprint for the vineyard of Languedoc-Roussillon is projected to increase fourfold compared to the current footprint, while it will rise threefold for the vineyard from the Loire Valley. The obtained LCA results emphasized the need to account for the impact of both climate change and extreme events on grape production under future climate change scenarios.

Life cycle assessment of Tehran Municipal solid waste during the COVID-19 pandemic and environmental impacts prediction using machine learning

Life cycle assessment and machine learning were combined to find the best option for Tehran's waste management for future pandemics. The ReCipe results showed the waste's destructive effects after COVID-19 were greater than before due to waste composition changes. Plastic waste has changed from 7.5 to 11%. Environmental burdens of scenarios were Sc-1 (increase composting to 50%) > Sc-3 > Sc-4 > Sc-b2 > Sc-5 > Sc-2 (increase recycling from 9 to 20%). The artificial neural network and gradient-boosted regression tree could predict environmental impacts with high R2. Based on the results, the environmental burdens of solid waste after COVID-19 should be investigated.

Recent advances in lignocellulosic and algal biomass pretreatment and its biorefinery approaches for biochemicals and bioenergy conversion

As the global demand for sustainable energy increases, lignocellulosic (such as agricultural residues, forest biomass, municipal waste, and dedicated energy crops) and algal (including macroalgae and microalgae) biomass have attracted considerable attention, because of their high availability of carbohydrates. This is a potential feedstock to produce biochemical and bioenergy. Pretreatment of biomass can disrupt their complex structure, increasing conversion efficiency and product yield. Therefore, this review comprehensively discusses recent advances in different pretreatments (physical, chemical, physicochemical, and biological pretreatments) for lignocellulosic and algal biomass and their biorefining methods. Life cycle assessment (LCA) which enables the quantification of the environmental impact assessment of a biorefinery also be introduced. Biorefinery processes such as raw material acquisition, extraction, production, waste accumulation, and waste conversion are all monitored under this concept. Nevertheless, there still exist some techno-economic barriers during biorefinery and extensive research is still needed to develop cost-effective processes.

Assessment and Prediction of Grain Production Considering Climate Change and Air Pollution in China

This study examines the spatial and temporal impacts of climate change on grain production in China. This is achieved by establishing a spatial error model consisting of four indicators: the climate, air pollution, economic behavior, and agricultural technology, covering 31 provinces in China from 2004 to 2020. These indicators are used to validate the spatial impacts of climate change on grain production. Air pollution data are used as instrumental variables to address the causality between climate and grain production. The regression results show that: First, climatic variables all have a non-linear “increasing then decreasing” effect on food production. Second, SO2, PM10, and PM2.5 have a negative impact on grain production. Based on the model, changes in the climatic production potential of grain crops can be calculated, and the future spatial layout of climate production can also be predicted by using random forests. Studies have shown that the median value of China’s grain production potential is decreasing, and the low value is increasing.

Closing Greenhouse Gas Emission Gaps of Staple Crops in China

China is facing the dual challenge of achieving food security and agricultural carbon neutrality. Developing spatially explicit crop emission profiles can help inform policy to mitigate agricultural greenhouse gases (GHGs), but previous life-cycle studies were conducted mostly at national and provincial levels. Here, we estimate county-level carbon footprint of China's wheat and maize production based on a nationwide survey and determine the contribution of different strategies to closing regional emission gaps. Results show that crop carbon footprint varies widely between regions, from 0.07 to 3.00 kg CO₂e kg^-1 for wheat and from 0.09 to 2.30 kg CO₂e kg^-1 for maize, with inter-county variation generally much higher than interprovince variation. Hotspots are mainly concentrated in Xinjiang and Gansu provinces, owing to intensive irrigation and high plastic mulch and fertilizer inputs. Closing the regional emission gaps would benefit mostly from increasing crop yields and nitrogen use efficiency, but increasing manure use (e.g., in Northeast, East, and Central China) and energy use efficiency (e.g., in North and Northwest China) can also make important contributions. Our county-level carbon footprint estimates improve upon previous broad-scale results and will be valuable for detailed spatial analysis and the design of localized GHG mitigation strategies in China.

Machine Learning Applications in Biofuels’ Life Cycle: Soil, Feedstock, Production, Consumption, and Emissions

Machine Learning (ML) is one of the major driving forces behind the fourth industrial revolution. This study reviews the ML applications in the life cycle stages of biofuels, i.e., soil, feedstock, production, consumption, and emissions. ML applications in the soil stage were mostly used for satellite images of land to estimate the yield of biofuels or a suitability analysis of agricultural land. The existing literature have reported on the assessment of rheological properties of the feedstocks and their effect on the quality of biofuels. The ML applications in the production stage include estimation and optimization of quality, quantity, and process conditions. The fuel consumption and emissions stage include analysis of engine performance and estimation of emissions temperature and composition. This study identifies the following trends: the most dominant ML method, the stage of life cycle getting the most usage of ML, the type of data used for the development of the ML-based models, and the frequently used input and output variables for each stage. The findings of this article would be beneficial for academia and industry-related professionals involved in model development in different stages of biofuel’s life cycle.

Exergy flow of rice production system in Italy: Comparison among nine different varieties

Exergy analysis is receiving considerable attention as an approach to be applied for making decisions toward moving to a sustainable and energy-efficient food supply chain. This study focuses on how the selection of variety affects the exergy flow of a paddy rice production system. In this regard, nine varieties of rice in Italy, the largest rice producer in Europe, were evaluated using the cumulative exergy analysis approach. Sensitivity analysis of inputs consumption and the exergy management scenarios of the most sensitive inputs are also provided in this study. The results indicated that the cumulative exergy consumption value of the investigated rice varieties ranges from 16.09 GJha^-1 to 25.80 GJ ha^-1. Fossil fuels and chemical fertilizer consumption were the most significant contributors to the total energy consumption in all investigated varieties. Luna variety, with the cumulative degree of perfection value of 7.96 and renewability indicator of 0.88, was identified as the most exergy-efficient variety of rice in Italy.

A Review on Machine Learning Application in Biodiesel Production Studies

The consumption of fossil fuels has exponentially increased in recent decades, despite significant air pollution, environmental deterioration challenges, health problems, and limited resources. Biofuel can be used instead of fossil fuel due to environmental benefits and availability to produce various energy sorts like electricity, power, and heating or to sustain transportation fuels. Biodiesel production is an intricate process that requires identifying unknown nonlinear relationships between the system input and output data; therefore, accurate and swift modeling instruments like machine learning (ML) or artificial intelligence (AI) are necessary to design, handle, control, optimize, and monitor the system. Among the biodiesel production modeling methods, machine learning provides better predictions with the highest accuracy, inspired by the brain’s autolearning and self-improving capability to solve the study’s complicated questions; therefore, it is beneficial for modeling (trans) esterification processes, physicochemical properties, and monitoring biodiesel systems in real-time. Machine learning applications in the production phase include quality optimization and estimation, process conditions, and quantity. Emissions composition and temperature estimation and motor performance analysis investigate in the consumption phase. Fatty methyl acid ester stands as the output parameter, and the input parameters include oil and catalyst type, methanol-to-oil ratio, catalyst concentration, reaction time, domain, and frequency. This paper will present a review and discuss various ML technology advantages, disadvantages, and applications in biodiesel production, mainly focused on recently published articles from 2010 to 2021, to make decisions and optimize, model, control, monitor, and forecast biodiesel production.

Life cycle assessment and energy comparison of aseptic ohmic heating and appertization of chopped tomatoes with juice

The energy balance and life cycle assessment (LCA) of ohmic heating and appertization systems for processing of chopped tomatoes with juice (CTwJ) were evaluated. The data included in the study, such as processing conditions, energy consumption, and water use, were experimentally collected. The functional unit was considered to be 1 kg of packaged CTwJ. Six LCA impact assessment methodologies were evaluated for uncertainty analysis of selection of the impact assessment methodology. The energy requirement evaluation showed the highest energy consumption for appertization (156 kWh/t of product). The energy saving of the ohmic heating line compared to the appertization line is 102 kWh/t of the product (or 65% energy saving). The energy efficiencies of the appertization and ohmic heating lines are 25% and 77%, respectively. Regarding the environmental impact, CTwJ processing and packaging by appertization were higher than those of ohmic heating systems. In other words, CTwJ production by the ohmic heating system was more environmentally efficient. The tin production phase was the environmental hotspot in packaged CTwJ production by the appertization system; however, the agricultural phase of production was the hotspot in ohmic heating processing. The uncertainty analysis results indicated that the global warming potential for appertization of 1 kg of packaged CTwJ ranges from 4.13 to 4.44 kg CO₂eq. In addition, the global warming potential of the ohmic heating system ranges from 2.50 to 2.54 kg CO₂eq. This study highlights that ohmic heating presents a great alternative to conventional sterilization methods due to its low environmental impact and high energy efficiency.

Estimation of Unit Process Data for Life Cycle Assessment Using a Decision Tree-Based Approach

Lacking unit process data is a major challenge for developing life cycle inventory (LCI) in life cycle assessment (LCA). Previously, we developed a similarity-based approach to estimate missing unit process data, which works only when less than 5% of the data are missing in a unit process. In this study, we developed a more flexible machine learning model to estimate missing unit process data as a complement to our previous method. In particular, we adopted a decision tree-based supervised learning approach to use an existing unit process dataset (ecoinvent 3.1) to characterize the relationship between the known information (predictors) and the missing one (response). The results show that our model can successfully classify the zero and nonzero flows with a very low misclassification rate (0.79% when 10% of the data are missing). For nonzero flows, the model can accurately estimate their values with an R² over 0.7 when less than 20% of data are missing in one unit process. Our method can provide important data to complement primary LCI data for LCA studies and demonstrates the promising applications of machine learning techniques in LCA.

Using the Machine Learning Method to Study the Environmental Footprints Embodied in Chinese Diet

The food system profoundly affects the sustainable development of the environment and resources. Numerous studies have shown that the food consumption patterns of Chinese residents will bring certain pressure to the environment. Food consumption patterns have individual differences. Therefore, reducing the pressure of food consumption patterns on the environment requires the precise positioning of people with high consumption tendencies. Based on the related concepts of the machine learning method, this paper designs an identification method of the population with a high environmental footprint by using a decision tree as the core and realizes the automatic identification of a large number of users. By using the microdata provided by CHNS(the China Health and Nutrition Survey), we study the relationship between residents’ dietary intake and environmental resource consumption. First, we find that the impact of residents’ food system on the environment shows a certain logistic normal distribution trend. Then, through the decision tree algorithm, we find that four demographic characteristics of gender, income level, education level, and region have the greatest impact on residents’ environmental footprint, where the consumption trends of different characteristics are also significantly different. At the same time, we also use the decision tree to identify the population characteristics with high consumption tendency. This method can effectively improve the identification coverage and accuracy rate and promotes the improvement of residents’ food consumption patterns.

Detection of Crop Seeding and Harvest through Analysis of Time-Series Sentinel-1 Interferometric SAR Data

Synthetic aperture radar (SAR) is more sensitive to the dielectric properties and structure of the targets and less affected by weather conditions than optical sensors, making it more capable of detecting changes induced by management practices in agricultural fields. In this study, the capability of C-band SAR data for detecting crop seeding and harvest events was explored. The study was conducted for the 2019 growing season in Temiskaming Shores, an agricultural area in Northern Ontario, Canada. Time-series SAR data acquired by Sentinel-1 constellation with the interferometric wide (IW) mode with dual polarizations in VV (vertical transmit and vertical receive) and VH (vertical transmit and horizontal receive) were obtained. interferometric SAR (InSAR) processing was conducted to derive coherence between each pair of SAR images acquired consecutively in time throughout the year. Crop seeding and harvest dates were determined by analyzing the time-series InSAR coherence and SAR backscattering. Variation of SAR backscattering coefficients, particularly the VH polarization, revealed seasonal crop growth patterns. The change in InSAR coherence can be linked to change of surface structure induced by seeding or harvest operations. Using a set of physically based rules, a simple algorithm was developed to determine crop seeding and harvest dates, with an accuracy of 85% (n = 67) for seeding-date identification and 56% (n = 77) for harvest-date identification. The extra challenge in harvest detection could be attributed to the impacts of weather conditions, such as rain and its effects on soil moisture and crop dielectric properties during the harvest season. Other factors such as post-harvest residue removal and field ploughing could also complicate the identification of harvest event. Overall, given its mechanism to acquire images with InSAR capability at 12-day revisiting cycle with a single satellite for most part of the Earth, the Sentinel-1 constellation provides a great data source for detecting crop field management activities through coherent or incoherent change detection techniques. It is anticipated that this method could perform even better at a shorter six-day revisiting cycle with both satellites for Sentinel-1. With the successful launch (2019) of the Canadian RADARSAT Constellation Mission (RCM) with its tri-satellite system and four polarizations, we are likely to see improved system reliability and monitoring efficiency.

Comparing Machine Learning Approaches for Predicting Spatially Explicit Life Cycle Global Warming and Eutrophication Impacts from Corn Production

Agriculture ranks as one of the top contributors to global warming and nutrient pollution. Quantifying life cycle environmental impacts from agricultural production serves as a scientific foundation for forming effective remediation strategies. However, methods capable of accurately and efficiently calculating spatially explicit life cycle global warming (GW) and eutrophication (EU) impacts at the county scale over a geographic region are lacking. The objective of this study was to determine the most efficient and accurate model for estimating spatially explicit life cycle GW and EU impacts at the county scale, with corn production in the U.S.’s Midwest region as a case study. This study compared the predictive accuracies and efficiencies of five distinct supervised machine learning (ML) algorithms, testing various sample sizes and feature selections. The results indicated that the gradient boosting regression tree model built with approximately 4000 records of monthly weather features yielded the highest predictive accuracy with cross-validation (CV) values of 0.8 for the life cycle GW impacts. The gradient boosting regression tree model built with nearly 6000 records of monthly weather features showed the highest predictive accuracy with CV values of 0.87 for the life cycle EU impacts based on all modeling scenarios. Moreover, predictive accuracy was improved at the cost of simulation time. The gradient boosting regression tree model required the longest training time. ML algorithms demonstrated to be one million times faster than the traditional process-based model with high predictive accuracy. This indicates that ML can serve as an alternative surrogate of process-based models to estimate life-cycle environmental impacts, capturing large geographic areas and timeframes.