Donghoon Lee , Frank Davenport , Shraddhanand Shukla , Greg Husak , Chris Funk , James Verdin
{"title":"Contrasting performance of panel and time-series data models for subnational crop forecasting in Sub-Saharan Africa","authors":"Donghoon Lee , Frank Davenport , Shraddhanand Shukla , Greg Husak , Chris Funk , James Verdin","doi":"10.1016/j.agrformet.2024.110213","DOIUrl":null,"url":null,"abstract":"<div><div>We comprehensively examine methodologies tailored for subnational crop yield and production forecasting by integrating Earth Observation (EO) datasets and advanced machine learning approaches. We scrutinized diverse input data types, cross-validation methods, and training durations, focusing on maize production and yield predictions in Burkina Faso and Somalia. Central to our analysis is the comparative assessment of using time-invariant features within a panel data (PD) model versus a time-series data (TD) model. The TD model performed well in predicting both production and yield, while the PD model offered comparable yield predictions. Time-invariant features such as livelihood zones, soil properties, and cropland extents enriched the spatial understanding of crop data, enhancing the R-squared by 0.09 (0.21) for production and 0.11 (0.03) for yield, with corresponding reductions in the Mean Absolute Percentage Error by 90 % (238 %) for production and 5 % (4 %) for yield in Burkina Faso (Somalia). While Burkina Faso's consistent crop data allowed for effective modeling with brief training, Somalia benefited from the adaptability of the PD model to crop statistics outliers, particularly with extended training in high-producing regions. The PD approach showed promise in addressing data gaps, although predicting crop productions for unobserved districts remained a challenge. Our findings highlight the harmonious integration of EO data and machine learning in the field of agricultural forecasting and emphasize the importance of region-specific methodologies, especially in the rapidly changing landscape of EO data convergence.</div></div>","PeriodicalId":50839,"journal":{"name":"Agricultural and Forest Meteorology","volume":"359 ","pages":"Article 110213"},"PeriodicalIF":5.6000,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Agricultural and Forest Meteorology","FirstCategoryId":"97","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0168192324003265","RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AGRONOMY","Score":null,"Total":0}
引用次数: 0
Abstract
We comprehensively examine methodologies tailored for subnational crop yield and production forecasting by integrating Earth Observation (EO) datasets and advanced machine learning approaches. We scrutinized diverse input data types, cross-validation methods, and training durations, focusing on maize production and yield predictions in Burkina Faso and Somalia. Central to our analysis is the comparative assessment of using time-invariant features within a panel data (PD) model versus a time-series data (TD) model. The TD model performed well in predicting both production and yield, while the PD model offered comparable yield predictions. Time-invariant features such as livelihood zones, soil properties, and cropland extents enriched the spatial understanding of crop data, enhancing the R-squared by 0.09 (0.21) for production and 0.11 (0.03) for yield, with corresponding reductions in the Mean Absolute Percentage Error by 90 % (238 %) for production and 5 % (4 %) for yield in Burkina Faso (Somalia). While Burkina Faso's consistent crop data allowed for effective modeling with brief training, Somalia benefited from the adaptability of the PD model to crop statistics outliers, particularly with extended training in high-producing regions. The PD approach showed promise in addressing data gaps, although predicting crop productions for unobserved districts remained a challenge. Our findings highlight the harmonious integration of EO data and machine learning in the field of agricultural forecasting and emphasize the importance of region-specific methodologies, especially in the rapidly changing landscape of EO data convergence.
期刊介绍:
Agricultural and Forest Meteorology is an international journal for the publication of original articles and reviews on the inter-relationship between meteorology, agriculture, forestry, and natural ecosystems. Emphasis is on basic and applied scientific research relevant to practical problems in the field of plant and soil sciences, ecology and biogeochemistry as affected by weather as well as climate variability and change. Theoretical models should be tested against experimental data. Articles must appeal to an international audience. Special issues devoted to single topics are also published.
Typical topics include canopy micrometeorology (e.g. canopy radiation transfer, turbulence near the ground, evapotranspiration, energy balance, fluxes of trace gases), micrometeorological instrumentation (e.g., sensors for trace gases, flux measurement instruments, radiation measurement techniques), aerobiology (e.g. the dispersion of pollen, spores, insects and pesticides), biometeorology (e.g. the effect of weather and climate on plant distribution, crop yield, water-use efficiency, and plant phenology), forest-fire/weather interactions, and feedbacks from vegetation to weather and the climate system.