Climate change impacts on US livestock production: a data-driven assessment

Red meat, derived from livestock such as cattle (beef), pigs (pork), sheep (lamb and mutton), and calves (veal), constitutes a vital component of global food systems. Characterized by its high myoglobin content, red meat is a rich source of high-quality protein, essential vitamins (B12, B6, and niacin), and minerals including iron, zinc, and phosphorus. Its nutritional significance, coupled with strong consumer demand, has positioned the red meat industry as a critical contributor to food security, economic development, and rural livelihoods worldwide. The United States stands as the largest producer of beef globally, accounting for approximately 20.5% of total production, with an annual output of around 12.3 million metric tons. The sector plays a central role in the national economy, supporting a vast ecosystem of farmers, ranchers, input suppliers, processors, and distributors, while generating substantial economic value (Taylor, 2024, December 16). However, the sustainability of this industry is increasingly threatened by climate change, evolving consumption patterns, and heightened environmental concerns (Waite et al., 2019).

Climate change represents a systemic and multifaceted risk to livestock production systems Barrozo (2021). Rising temperatures, erratic precipitation patterns, and the increasing frequency of extreme weather events are disrupting traditional farming practices and affecting productivity. Livestock are particularly vulnerable to heat stress, which reduces growth rates, fertility, and overall health, while increasing susceptibility to diseases. Simultaneously, farmers face declining pasture quality, water scarcity, and escalating input costs, all of which compromise operational efficiency and profitability. In addition to these production challenges, the environmental footprint of red meat production has come under significant scrutiny. The livestock sector is resource-intensive, requiring substantial inputs of land, feed, and water. It is also a major contributor to greenhouse gas emissions, particularly methane (CH₄) and carbon dioxide (CO₂) (Lu, 2024, August 18). According to the Food and Agriculture Organization, livestock accounts for approximately 14.5% of global greenhouse gas emissions, with cattle contributing the largest share. These environmental externalities have intensified the urgency for transitioning toward more sustainable and climate-resilient production systems.

Against this backdrop, this study investigates the impact of climate change on meat production and livestock farming in the United States using a data-driven analytical framework. Drawing on secondary data from the Food and Agriculture Organization and the United States Department of Agriculture, the research employs exploratory data analysis and statistical techniques to examine the relationships between key climatic variables—such as temperature and rainfall variability—and livestock productivity and cost structures across regions. The study further integrates a sustainability and business innovation perspective by identifying region-specific vulnerabilities and opportunities for adaptation. The findings highlight significant spatial disparities in climate impact, underscoring the need for localized and targeted interventions. In response, the research explores adaptive strategies including precision livestock farming, climate-smart agricultural practices, alternative feed innovations, and the development of climate-resilient breeds. Additionally, emerging technological solutions such as digital monitoring systems and alternative protein sources, including cultured meat (Lynch and Pierrehumbert, 2019), are considered as part of a broader transition toward sustainable agri-food systems.

By bridging climate science, data analytics, and business strategy, this study contributes to the evolving discourse on sustainable livestock management. It offers actionable insights for policymakers, agribusiness firms, and farming communities to enhance resilience, ensure economic viability, and support environmental stewardship. Ultimately, the research aims to advance adaptive pathways that safeguard food security and livelihoods while aligning the red meat industry with long-term sustainability goals.

The relationship between climate change and livestock production has been extensively examined across environmental, economic, and technological dimensions. Existing literature highlights both the vulnerability of livestock systems to climatic stressors and their contribution to greenhouse gas (GHG) emissions, while also proposing adaptive and mitigation strategies for sustainable transformation.

A foundational understanding is provided by studies which outline the direct and indirect effects of climate change on livestock systems. Key direct impacts include heat stress, reduced feed intake, declining reproductive efficiency, and increased disease susceptibility, all of which adversely affect productivity. Indirect effects—such as deterioration in forage quality, water scarcity, and seasonal variability—further compound these challenges. Importantly, the livestock sector is identified as a significant contributor to global emissions, particularly methane (CH₄), nitrous oxide (N₂O), and carbon dioxide (CO₂), arising from enteric fermentation, manure management, and land-use changes. These findings underscore the dual role of livestock as both a victim and driver of climate change (Cheng et al., 2022).

Complementing this perspective, cross-country empirical analyses, such as the study on agricultural productivity in Asian economies, reveal the temporal complexity of climate impacts. Using advanced panel econometric techniques (ARDL models), the research demonstrates that while carbon fertilization effects may temporarily enhance productivity, long-term impacts of rising temperatures and erratic rainfall are predominantly negative (Ozdemir et al., 2021). Similarly, non-linear modeling evidence from Pakistan highlights asymmetric effects of climate variables on livestock productivity, suggesting that climate impacts are context-specific and vary across regions and production systems (Khurshid et al., 2023).

Region-specific vulnerability is further emphasized in studies conducted in developing economies. For instance, research on Ethiopia identifies drought as a critical driver of livestock mortality, pasture degradation, and productivity loss, while also documenting adaptive strategies such as herd diversification and mobility (Bogale and Erena, 2022). These findings reinforce the need for localized adaptation frameworks, particularly in climate-sensitive regions.

A significant body of literature employs advanced modeling techniques to quantify climate impacts. For example, bioenergetic and climate-integrated models using CMIP6 datasets estimate reductions in dry matter intake (DMI) due to heat stress and their consequent effects on global cattle productivity (Thornton et al., 2022). Similarly, Temperature-Humidity Index (THI)-based models project a substantial increase in extreme heat stress events across livestock species under future climate scenarios (Thornton et al., 2021). These studies consistently highlight severe productivity losses, particularly in tropical regions, and stress the urgency of adaptive interventions.

Methodologically, recent research demonstrates a shift toward integrative and data-driven approaches. Systematic literature reviews and meta-analyses, such as those following PRISMA frameworks, quantify the effects of heat stress on livestock welfare and productivity, incorporating both biological and socio-economic dimensions (Morgado et al., 2022). Other studies combine satellite data with machine learning techniques—including LSTM, XGBoost, and ARIMA—to enhance the precision of GHG emission tracking and forecasting (Jobarteh and Neethirajan, 2025). These approaches reflect the growing importance of advanced analytics in sustainability research.

Sector-specific analyses further deepen the understanding of climate impacts. Research on poultry and broiler production highlights challenges such as heat stress, water scarcity, and increased emissions, while proposing adaptive strategies including improved housing, genetic selection, and precision feeding (Attia et al., 2024; Emmanuel et al., 2024). Similarly, studies on beef production emphasize the role of sustainable grazing, feed efficiency, and technological integration in reducing environmental footprints (Hubbart, 2023). Innovative approaches, such as the use of tree cover to mitigate heat stress in cattle, demonstrate the potential of nature-based solutions in enhancing productivity and resilience (Richards et al., 2015; Horton, 2024, August 9).

From a systems perspective, dynamic modeling studies explore long-term trade-offs between productivity and sustainability under resource constraints. For instance, simulations in Portugal's livestock sector reveal that reducing herd size while improving individual productivity can balance emission reduction with production goals. Additionally, global food security models highlight the interplay between population growth, land use, and climate change, emphasizing the broader implications of livestock systems within the agri-food ecosystem (Molotoks et al., 2021).

Beyond production, consumer behavior and corporate responsibility also influence the sustainability trajectory of the meat industry. Studies indicate that while environmental concerns are rising, consumer purchasing decisions remain primarily driven by price, quality, and health considerations (Rolfe et al., 2023). At the corporate level, large meat and dairy producers have been criticized for insufficiently addressing emissions beyond energy use, particularly methane and land-use impacts, highlighting gaps in climate accountability (Lazarus et al., 2021).

Despite the breadth of existing research, several gaps remain. Many studies focus predominantly on ruminant livestock, with limited attention to non-ruminant species and integrated systems. There is also a lack of hyper-localized, data-driven analyses that combine climatic, economic, and production variables at granular levels. Furthermore, while advanced modeling techniques are increasingly used, their application in bridging sustainability, business strategy, and regional policy interventions remains underexplored.

In summary, the literature establishes that climate change poses significant risks to livestock production through both direct and indirect pathways, while also identifying the sector's contribution to global emissions. It highlights the need for climate-smart practices, technological innovation, and policy-driven interventions. However, there remains a critical need for integrated, data-driven, and region-specific studies that can provide actionable insights for enhancing resilience and sustainability in livestock systems.

Although the overall potential effects of climate change on climate-related red meat are well-documented (with the major effects being climatically induced heat stress, GHG emissions, and overall livestock productivity), there is a big deficit in terms of understanding the inter-relationships of climate variables (temperature, humidity, CO2) and the type of red meat (beef, pork, lamb, veal) to be produced, as well as current production systems in different regions across the United States (Steinfeld et al., 2006). Most studies recommend region-wise research as there are variations in the parameters of climate change.

Moreover, the literature commonly focuses on the mitigation measures (e.g. genetic selection, feed modifications); it is currently deficient in supporting large evidence-based research that predicts longevity through powerful machine learning techniques to measure future local effects according to various climatic conditions. There is a need to evaluate the joint impact of multiple stressors acting in one time slot (e.g. high humidity and heat) and provide practical, regional-specific concepts of adaptation, with respect to certain areas in the United States and types of red meat.

The current study intends to fill this research gap by incorporating regionally disaggregated climate and production data through a machine learning approach. The study focuses on the prediction of sustainable red meat production through evidence-based input that supports specific climate adaptation and provides granular adaptation recommendations based on current U.S. climate realities.

The United States is the top global red meat producer, primarily beef, with an estimated 2023 production of about 26.96 billion pounds (or 59.96 million metric tons for the 2023/2024 marketing year). The USDA's Foreign Agricultural Service (FAS) also projects continued growth, with 2024/2025 production forecast at 61.66 million metric tons. However, climate change has significantly impacted agricultural and livestock productivity in the United States, posing challenges to the production of red meat. Variations in climate factors such as temperature, humidity, and CO₂ levels affect cattle health, feed availability, and overall yield. There is a need to study and understand these factors and control them through human intervention.

1. To analyze the impact of climate change factors such as temperature, humidity, and CO₂ levels on red meat production in the United States through a data-driven approach.

2. To develop predictive models leveraging machine learning techniques to forecast future trends in beef production under changing climate conditions.

3. To provide data-driven insights and recommendations for policymakers and industry stakeholders to mitigate the adverse effects of climate change on livestock productivity.

Data for this study have been collected from reliable government sources, including:

1. United States Department of Agriculture (USDA): Provides historical records on livestock productivity, meat production trends, feed consumption, and economic aspects of meat production.

2. National Centers for Environmental Information (NOAA Climate at a Glance): Offers long-term climate data, including temperature trends, precipitation records, and extreme weather events from 1910 to 2024.

Tools used are Tableau Public, Python, and R Studio.

The trend of red meat production over time, as depicted in Figure 1 – Trend of Red Meat Production over Time, shows a steady and significant increase from the 1940s to recent years. The blue line represents the actual production values, while the dashed trend line highlights the overall upward trajectory. Initially, production levels were around 20,000 metric tons, but over time, they have more than doubled, reaching approximately 50,000 metric tons in the most recent years.

The fluctuations in the production line suggest periodic variations, possibly due to seasonal effects, economic factors, climate conditions, and shifts in consumer demand. Despite these fluctuations, the long-term growth trend remains positive, indicating advancements in livestock farming, improved agricultural techniques, and increasing global demand for red meat.

However, the recent decline towards the end of the timeline suggests potential disruptions in the industry, which could be linked to factors such as climate change, regulatory policies, shifts in dietary preferences, or economic downturns. This trend emphasizes the need for sustainable livestock management strategies to ensure the future stability of red meat production.

The seasonal analysis of monthly average red meat production, as shown in Figure 2, indicates relatively stable production levels throughout the year, with minor fluctuations across different months. The box plot representation suggests that the production of red meat does not exhibit extreme variations, implying that seasonal effects do not significantly impact overall production trends.

However, February appears to have slightly lower production levels, likely due to the shorter number of days in the month, affecting total output. Conversely, October and November show a slight increase in production, possibly driven by higher demand during the holiday season, including Thanksgiving and other festivities.

The relatively consistent production pattern across months suggests that red meat processing and supply chains operate at a steady rate year-round, ensuring a stable market supply. While external factors such as climate variations, feed availability, or economic conditions may influence production, no major seasonal disruptions are evident from this visualization.

The analysis of various red meat production trends from the mid-1900s to 2022 in Figure 3 reveals clear patterns in the production of beef, pork, lamb, mutton, and veal.

1. Beef production (orange area) has shown consistent growth, peaking around the early 2000s and maintaining a high production level since then. This indicates the strong demand and supply efficiency in the beef industry.

2. Pork production (red area) has also demonstrated steady growth, particularly in the last few decades, suggesting increasing consumer preference and improved farming techniques.

3. Lamb & Mutton production (green area), however, has declined significantly over time. The sharp decrease in the mid-20th century suggests a declining market share, possibly due to changing consumer preferences, higher production costs, or competition from other meat sources.

4. Veal production (grey area) has also witnessed a dramatic decline, particularly after the 1970s. This could be attributed to ethical concerns, regulatory restrictions, and reduced consumer demand for veal meat.

The Yearly Production Comparison of Beef heatmap given in Figure 4 provides insights into the month-wise variations in beef production over the years from 2009 to 2024. The intensity of the shading represents the level of production, with darker shades indicating lower production levels and lighter shades representing higher production volumes.

From the heatmap, it appears that beef production has remained relatively stable throughout the years, with some fluctuations in specific months. Notably, certain months in different years show slightly lighter shades, suggesting temporary increases in production. The year 2020, for instance, shows noticeable variation, likely influenced by external disruptions such as the COVID-19 pandemic, which affected supply chains, labor availability, and market demand.

While there is no extreme seasonality visible, the subtle variations across months suggest periodic shifts in beef production due to external factors such as market demand, climate variations, or economic influences. This visualization helps in understanding long-term production patterns and identifying any potential anomalies or shifts in beef production trends over time.

Regression Analysis was conducted to observe the impact of the various climate factors on red meat production as given in Figure 5.

1. R-squared (R²): 0.93 (This means that 93% of the variation in red meat production is explained by climate variables.)

2. Mean Absolute Error (MAE): 0.0567 (On average, predictions deviate from actual values by 0.0567 units in the normalized scale.)

3. Mean Squared Error (MSE): 0.0038 (A small error value, indicating a good fit.)

4. Root Mean Squared Error (RMSE): 0.0617 (Lower RMSE suggests high prediction accuracy.)

1. CO₂ Level (p-value = 0.00008) is statistically significant (p-value <0.05), meaning CO₂ levels have a strong impact on red meat production.

2. Temperature (p-value = 0.54) and Humidity (p-value = 0.38) are not statistically significant, indicating they may not have a strong direct effect on red meat production. Multicollinearity Check (VIF):

3. Humidity (VIF = 161.26) and CO₂ Level (VIF = 155.70) are highly collinear, meaning they are strongly correlated with each other, which can distort model performance.

4. Temperature (VIF = 1.59) is within acceptable limits (VIF <10).

Most of the points are closely aligned with the red line, indicating that the model has a high predictive accuracy, as given in Figure 6.

1. A few points are slightly scattered away from the perfect prediction line, which means some errors exist, but they are relatively small.

2. This suggests that the model captures the overall trend very well, which aligns with the high R² score (0.93). The model has strong predictive power, as most predicted values match the actual values closely.

Various models were built, and a comparison was conducted to identify the best one.

1. It has the lowest MAE (158.52) and the lowest MSE (38197.77).

2. It also has the highest R² Score (0.9472), meaning it explains 94.72% of the variance in the target variable.

3. This suggests that Gradient Boosting captures complex relationships in the data better than the other models.

1. Its MAE (170.63) and MSE (44708.54) are slightly higher than Gradient Boosting. The R² Score (0.9382) is still high, but slightly lower than Gradient Boosting. This means Random Forest is a strong model, but not as optimized as Gradient Boosting.

1. It has the highest MAE (193.77) and MSE (57334.12), meaning its predictions are less accurate.

2. The lowest R² Score (0.9207) indicates that it explains less variance than Gradient Boosting and Random Forest.

3. Linear Regression is a simpler model and may not capture complex patterns as well as tree-based models.

The feature importance analysis depicted in Figure 7 compares Random Forest, Gradient Boosting, and Linear Regression, highlighting which climate variables (Average Temperature, Humidity, and CO₂ Level) most influence red meat production in each model. This is represented in a tabular format in Table 2.

1. CO₂ Level is the Most Influential Feature in Random Forest (0.967). In the Random Forest model, CO₂ Level has an overwhelming 96.7% importance, meaning it plays a dominant role in predicting red meat production. Humidity (0.0176) and Temperature (0.0153) contribute very little, indicating Random Forest does not find them strongly predictive.

2. Humidity is the Most Important Feature in Gradient Boosting (0.983). In Gradient Boosting, Humidity (98.3%) is the most significant predictor, while CO₂ Level (0.0093) and Temperature (0.0074) contribute minimally. This suggests that Gradient Boosting captures a complex, non-linear relationship between humidity and red meat production, which is missed by other models.

3. Linear Regression Shows High Sensitivity to CO₂ Level and Humidity. In Linear Regression, CO₂ Level (22.26) and Humidity (10.89) have large coefficients, while Temperature (1.70) is the least impactful. The large values indicate a strong linear relationship, but since Linear Regression assumes strict linearity, it may not fully capture non-linear interactions.

The correlation heatmap given in Figure 8 provides a comprehensive view of the relationships between climate factors (Average Temperature, Humidity, and CO₂ Levels) and red meat production variables (Beef, Veal, Pork, Lamb & Mutton, and Total Red Meat). The Total Red Meat production has a strong positive correlation with CO₂ Levels (0.96) and Pork production (0.94), suggesting that higher CO₂ levels are associated with increased red meat production, possibly due to improved feed availability or agricultural conditions.

Humidity also shows a high correlation with Total Red Meat (0.95), Pork (0.92), and Beef (0.87), indicating that humidity might influence livestock health, feed intake, or meat yield. Interestingly, Temperature exhibits a strong negative correlation with meat production (−0.91 with Total Red Meat, −0.94 with Beef, and −0.95 with Pork), suggesting that higher temperatures could negatively impact livestock productivity, likely due to heat stress, reduced metabolism, or feed inefficiencies.

The negative correlation between temperature and CO₂ (−0.95) suggests an inverse climate effect, where rising temperatures may counteract the benefits of increased CO₂ levels. Overall, CO₂ and Humidity appear to be strong positive drivers of red meat production, while higher temperatures have an adverse effect, indicating that climate change dynamics may have complex, contrasting impacts on livestock industries.

1. Steady Long-Term Growth – Beef production in Figure 9 has shown a consistent upward trend from the 1940s to recent years, indicating industry growth and increased demand.

2. Short-Term Fluctuations – Noticeable seasonal and periodic variations suggest production is influenced by external factors like climate conditions, market demand, and livestock cycles.

3. Recent Stabilization – Post-2000, production growth slows down with more fluctuations, possibly due to climate change effects, sustainability concerns, or shifting dietary trends.

The moving average plot of beef production over time depicted in Figure 10, highlights long-term trends and fluctuations. From the 1940s to around the 1980s, beef production exhibited steady growth, followed by a volatile but increasing trend until the 2000s. In the last decade, production appears to have stabilized with some fluctuations, suggesting that external factors such as climate change, economic conditions, feed availability, or policy interventions might be influencing production. The shaded region towards the right represents the forecasted period, with a confidence interval indicating possible variation in predictions.

The forecasted beef production values from September 2024 to August 2026 is given in Table 3. The Point Forecast column provides the predicted values, while the Lo 80, Hi 80, Lo 95, and Hi 95 columns represent the 80% and 95% confidence intervals, respectively. These intervals show the range within which future beef production is expected to fall with a high degree of confidence. The projections indicate that beef production will fluctuate between 2,100 and 2,300 units in 2024–2025, with a slight increasing trend in 2026, suggesting a potential recovery or stabilization in output.

However, the presence of confidence intervals highlights the uncertainty in predictions, which could be influenced by climate conditions, market demand, or livestock management practices.

The forecast suggests that beef production is not expected to decline sharply, but there may be moderate variations influenced by external factors. The moving average trend confirms a historical increase with some periodic declines, while the forecasted values suggest stabilization with possible fluctuations. Further analysis incorporating climate data, feed availability, and policy changes could provide deeper insights into the long-term sustainability of beef production.

1. Consistent Upward Trend – Humidity levels given in Figure 11 shows a steady increase from the 1940s to 2024, indicating long-term climate changes.

2. Seasonal and Short-Term Variations – Frequent fluctuations suggest periodic changes, possibly due to weather patterns, regional climate shifts, or seasonal cycles.

3. Acceleration in Recent Years – The rate of increase appears higher post-2000, which may be linked to rising global temperatures and increased moisture retention in the atmosphere due to climate change.

A moving average trend of humidity over time shows a consistent upward trend from the 1940s to the present as given in Figure 12. The steady increase in humidity levels suggests a long-term climate shift, possibly linked to global warming, changing precipitation patterns, or atmospheric moisture retention due to rising temperatures. Unlike other climatic variables that may exhibit fluctuations, humidity shows a strong and continuous increasing pattern, indicating that external climate influences are persistently driving moisture levels higher. The forecasted region (shaded area) towards the right suggests continued humidity increase with a small margin of uncertainty.

The forecasted humidity values from September 2024 to August 2026 given in Table 4, provide a point forecast along with 80% and 95% confidence intervals. The forecasted values range between 80.0 and 80.5, indicating a gradual increase in humidity over the next two years. The confidence intervals show narrow variability, implying that the model is certain about the papered increase. This sustained rise in humidity could have significant implications for agriculture, livestock farming, and human health, as increased humidity can lead to heat stress, changes in precipitation, and impacts on ecosystems.

Overall, the forecast aligns with historical trends, confirming that humidity is on a long-term upward trajectory. This trend may exacerbate the effects of temperature rise on agriculture, particularly livestock farming, where higher humidity combined with heat could reduce animal productivity. Further analysis on regional variations and correlations with other climate factors (such as temperature and CO₂ levels) would provide deeper insights into how this increasing humidity impacts different industries. Incorporating external drivers such as pricing dynamics, evolving consumer health preferences, and environmental concerns strengthens data analysis by providing contextual depth. These factors influence demand patterns, production decisions, and market volatility, enabling more accurate interpretation of trends and improving the robustness, relevance, and predictive capability of analytical models in meat production studies. These can be explored further.

Humidity and CO₂ Levels have shown a steady increase from the 1940s to the present. The moving average trend of humidity suggests a consistent rise, likely due to climate change effects on atmospheric moisture retention. CO₂ levels have also increased, which could be linked to industrial emissions and deforestation. Temperature exhibits a fluctuating pattern but generally follows an increasing trend. This implies potential long-term warming effects, which may negatively impact livestock farming due to heat stress and reduced feed efficiency.

Red Meat Production Trends:

Overall, red meat production has increased over time, but with periods of volatility. Beef production showed rapid growth from the 1940s until around 1980, followed by fluctuations in recent decades, likely due to market demand shifts, feed availability, and climate stress. Recent forecasts suggest stabilization in production levels, with minor fluctuations predicted for the next two years.

CO₂ Levels have a strong positive correlation with total red meat production (0.96 correlation). This suggests that increased CO₂ may be contributing to better feed availability (enhanced plant growth), indirectly supporting livestock farming. Humidity also has a strong positive correlation with red meat production (0.95).

This was unexpected, but it could indicate that regional variations were moderate humidity favors livestock growth. Temperature has a strong negative correlation with meat production (−0.91). Higher temperatures likely stress livestock, reducing growth rates and productivity.

Linear Regression Model Findings: The R² score (0.92) suggests that climate factors explain 92% of the variation in red meat production. CO₂ Level had the highest impact on red meat production, followed by Humidity. Temperature showed a negative impact, reinforcing the hypothesis that rising temperatures reduce livestock productivity.

1. Gradient Boosting performed best (R² = 0.947, lowest error).

2. Random Forest was slightly behind (R² = 0.938).

3. Linear Regression had the lowest performance (R² = 0.92), indicating that tree-based models captured complex relationships better.

Gradient Boosting identified Humidity as the most important feature (98.3% impact). This indicates that humidity plays a crucial role in red meat production, likely influencing livestock metabolism through the impact of heat stress. Random Forest highlighted CO₂ Level as the most important factor (96.7%). This aligns with the correlation analysis and supports the theory that CO₂-driven plant growth indirectly benefits livestock feed supply. Linear Regression showed high dependency on both CO₂ Level and Humidity, but its rigid assumption of linearity may not fully capture nonlinear interactions.

Beef Production Forecast (2024–2026). Predicted values suggest stabilization with slight fluctuations around 2,100–2,300 units. The confidence intervals show moderate uncertainty, possibly due to external market or climate influences. Humidity Forecast (2024–2026), expected to continue rising steadily, reaching around 80.5% by 2026. This aligns with historical upward trends, reinforcing concerns about rising heat stress effects on livestock.

1. The analysis showed a strong negative correlation between temperature and red meat production (−0.91).

2. Rising temperatures reduce livestock feed efficiency, increase mortality rates, and cause heat stress, leading to lower meat production.

1. Feature importance analysis identified humidity as the most influential variable in Gradient Boosting (98.3%).

2. High humidity contributes to increased disease spread, poor ventilation, and reduced feed conversion efficiency.

CO₂ levels showed a strong positive correlation (0.96) with total red meat production, suggesting that higher CO₂ concentrations enhance plant growth, leading to better livestock feed availability.

1. Increased CO₂ contributes to higher crop yields, which supports the livestock industry by ensuring a stable feed supply.

The current study successfully analyzed the impact of climate factors (Temperature, Humidity, and CO₂ Levels) on red meat production using regression analysis, feature importance evaluation, and forecasting techniques. The findings indicate that CO₂ levels and humidity have a strong positive correlation with meat production, suggesting that increased CO₂ may enhance feed availability, while humidity plays a crucial role in livestock productivity. In contrast, temperature negatively impacts red meat production, likely due to heat stress reducing livestock growth and efficiency. Among the predictive models tested, Gradient Boosting performed best, demonstrating superior accuracy in forecasting future production trends. The forecasting results show stable but slightly fluctuating beef production from 2024 to 2026, while humidity is expected to continue its steady rise, potentially exacerbating climate-related challenges for the livestock industry. These findings highlight the necessity of adaptive climate strategies in livestock management, including heat stress mitigation, humidity control, and enhancements in sustainable feed supply, to ensure resilient and efficient meat production amid climate change.