How Climate Factors Impact Fig Production Efficiency Using Machine Learning

Jenn Hoskins
1st June, 2024

How Climate Factors Impact Fig Production Efficiency Using Machine Learning

Image Source: Natural Science News, 2024

Key Findings

  • The study by Iğdır University in Turkey used machine learning to analyze how climate change affects fig production
  • Temperature change was found to have the highest impact on fig production, contributing over 40% in both models used
  • Other significant climate factors influencing fig production include thermal radiation and 2-meter temperature, while wind speed, precipitation, and humidity had lesser impacts
The impact of climate change on agriculture is a pressing issue, particularly for regions heavily reliant on specific crops. A recent study conducted by Iğdır University[1] employs machine learning to investigate how climate change influences fig production in Turkey. This study is crucial as fig production is a significant part of Turkey's agricultural economy, and understanding these impacts can help develop sustainable agricultural practices. The study uses the eXtreme Gradient Boosting (XGBoost) algorithm, a powerful machine learning tool, to analyze fig production performance and climate data from 1988 to 2023. The researchers created two models: one for fig production yield per decare (a unit of area) and another for fig production yield per bearing fig sapling. They included sixteen climate variables, considering both day and night values, to determine their influence on fig production. The models revealed that temperature change has the highest impact on fig production, contributing 41.30% in the first model and 43.90% in the second model. Other significant factors include thermal radiation and 2-meter temperature. Wind speed, precipitation, and humidity were found to have a lesser impact. This study's findings align with previous research on the broader impacts of climate change on agriculture. For instance, similar to how climate change affects fig production in Turkey, it also impacts rice production in Bangladesh. A study comparing the performance of ARIMA and XGBoost models found that XGBoost was more effective in predicting annual rice production, which is expected to increase despite climate challenges[2]. This highlights the utility of machine learning models in agricultural forecasting under changing climatic conditions. Moreover, the findings resonate with research on plant disease outbreaks and their relation to climate change. Climate change alters pathogen evolution and host-pathogen interactions, increasing the risk of plant disease outbreaks, which can significantly affect agricultural productivity[3]. The study on fig production underscores the importance of understanding specific climatic factors to mitigate these risks. The study also draws parallels with research on food security and agricultural land use. Climate variables such as land surface temperature, precipitation, and soil moisture have been shown to correlate with agricultural land and frost-affected areas, impacting food security[4]. The negative impact of temperature change on fig production efficiency in Turkey adds to the body of evidence that climate change poses a significant threat to agriculture and food security globally. In conclusion, the study by Iğdır University highlights the intricate relationship between climate change and fig production in Turkey. By utilizing machine learning models like XGBoost, the research provides valuable insights into the specific climatic factors affecting fig production. This approach not only aids in predicting future production trends but also informs the development of sustainable agricultural practices. These findings contribute to the broader understanding of how climate change impacts various agricultural sectors, supporting efforts to enhance food security and sustainability.

AgricultureEnvironmentPlant Science

References

Main Study

1) Investigating the effect of climate factors on fig production efficiency with machine learning approach.

Published 31st May, 2024

https://doi.org/10.1002/jsfa.13619


Related Studies

2) A tree based eXtreme Gradient Boosting (XGBoost) machine learning model to forecast the annual rice production in Bangladesh.

https://doi.org/10.1371/journal.pone.0283452


3) Climate change impacts on plant pathogens, food security and paths forward.

https://doi.org/10.1038/s41579-023-00900-7


4) An integrated approach of remote sensing and geospatial analysis for modeling and predicting the impacts of climate change on food security.

https://doi.org/10.1038/s41598-023-28244-5



Related Articles

An unhandled error has occurred. Reload 🗙