Abstract
This study developed a rapid rice yield estimation workflow and customized yield prediction model by integrating remote sensing and meteorological data with machine learning (ML). Several issues need to be addressed while developing a crop yield estimation model, including data quality issues, data processing issues, selecting a suitable machine learning model that can learn from few available time-series data, and understanding the non-linear relationship between historical crop yield and remote sensing and meteorological factors. This study applied a series of data processing techniques and a customized ML model to improve the accuracy of crop yield estimation at the district level in Nepal. It was found that remote sensing-derived NDVI product alone was not sufficient for accurate estimation of crop yield. After incorporating other meteorological variables into the ML models, estimation accuracy improved dramatically. Along with NDVI, the meteorological variables of rainfall, soil moisture, and evapotranspiration also exhibited a strong association with rice yield. This study also found that stacking multiple tree-based regression models together could achieve better accuracy than benchmark linear regression or standalone ML models. Due to the unique and distinct physio-geographical setting of each district, a variation in estimation accuracy from district to district could be observed. Our data processing and ML model workflow achieved an average of 92% accuracy of yield estimation with RMSE 328.06 kg/ha and MAE 317.21 kg/ha. This methodological workflow can be replicated in other study areas and the results can help the local authorities and stakeholders understand the factors affecting crop yields as well as estimating crop yield before harvesting season to ensure food security and sustainability.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 8
Claim · model-written summary
NDVI alone was insufficient for accurate rice yield estimation.
Not reportedTaxon
Verbatim
e0“remote sensing-derived NDVI product alone was not sufficient for accurate estimation of crop yield”
Claim · model-written summary
Adding meteorological variables markedly improved yield estimation accuracy.
- Outcome
- estimation accuracye0
- Direction
- improved dramaticallye0
- Comparator
- other meteorological variablese0
Not reportedTaxon
Verbatim
e0“After incorporating other meteorological variables into the ML models, estimation accuracy improved dramatically”
Claim · model-written summary
Rainfall, soil moisture and evapotranspiration, along with NDVI, were strongly associated with rice yield.
- Taxon
- rice
Oryza sativae0 - Outcome
- rice yielde0
- Direction
- strong associatione0
Not reportedSetting
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Along with NDVI, the meteorological variables of rainfall, soil moisture, and evapotranspiration also exhibited a strong association with rice yield”
Claim · model-written summary
Stacked tree regression models outperformed linear regression and individual ML models in yield accuracy.
Not reportedTaxon
Verbatim
e0“stacking multiple tree-based regression models together could achieve better accuracy than benchmark linear regression or standalone ML models”
Claim · model-written summary
Yield estimation accuracy varied among districts.
Not reportedTaxon
Verbatim
e0“a variation in estimation accuracy from district to district could be observed”
Claim · model-written summary
The workflow reached 92% average yield estimation accuracy.
Not reportedTaxon
Verbatim
e0“Our data processing and ML model workflow achieved an average of 92% accuracy of yield estimation”
Claim · model-written summary
The workflow had RMSE of 328.06 kg/ha.
Verbatim
e0“RMSE 328.06 kg/ha”
Claim · model-written summary
The workflow had MAE of 317.21 kg/ha.
Verbatim
e0“MAE 317.21 kg/ha”