Normalized difference vegetation index prediction using reservoir computing and pretrained language models
In this study, we examined plant health prediction through the Normalized Difference Vegetation Index (NDVI) calculated from satellite image derived reflectance values in the near-infrared and red spectra. The problem is formulated as a temporal data prediction problem. Using MODIS/Terra Vegetation...
Saved in:
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
KeAi Communications Co., Ltd.
2025-03-01
|
Series: | Artificial Intelligence in Agriculture |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2589721724000539 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
_version_ | 1832595312232890368 |
---|---|
author | John Olamofe Ram Ray Xishuang Dong Lijun Qian |
author_facet | John Olamofe Ram Ray Xishuang Dong Lijun Qian |
author_sort | John Olamofe |
collection | DOAJ |
description | In this study, we examined plant health prediction through the Normalized Difference Vegetation Index (NDVI) calculated from satellite image derived reflectance values in the near-infrared and red spectra. The problem is formulated as a temporal data prediction problem. Using MODIS/Terra Vegetation Indices 16-Day L3 Global 250 m SIN Grid V061 dataset, we designed and implemented Reservoir Computing (RC) models and transformer-based models including pretrained language model, and compared the prediction performance of these models to traditional machine learning and deep learning methods such as Nonlinear Regression, Decision Tree, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) network, and DLinear. It is observed that the DLinear/LSTM model showed exceptional predictive accuracy, while the pretrained RC model significantly enhanced traditional RC model forecasts. Additionally, Frozen Pretrained Transformer (FPT), a pretrained language model, showed superior performance in predicting specific NDVI values (most often peak or lowest NDVI), suggesting its effectiveness in precise temporal predictions. Furthermore, transformer-based models, specifically PatchTST and FPT, demonstrated substantial mean squared error reductions, particularly in limited data scenarios (1 %, 5 %, 15 % and 50 % sample sizes), indicating their robustness in precise NDVI temporal predictions when data is limited. The findings in this study demonstrated the effectiveness of emerging machine learning techniques such as reservoir computing and pretrained language model for remote sensing and their contributions in precision agriculture. |
format | Article |
id | doaj-art-29152a11148b4db19ffa656ac6cf2448 |
institution | Kabale University |
issn | 2589-7217 |
language | English |
publishDate | 2025-03-01 |
publisher | KeAi Communications Co., Ltd. |
record_format | Article |
series | Artificial Intelligence in Agriculture |
spelling | doaj-art-29152a11148b4db19ffa656ac6cf24482025-01-19T06:26:32ZengKeAi Communications Co., Ltd.Artificial Intelligence in Agriculture2589-72172025-03-01151116129Normalized difference vegetation index prediction using reservoir computing and pretrained language modelsJohn Olamofe0Ram Ray1Xishuang Dong2Lijun Qian3CREDIT Center and Electrical and Computer Engineering Department, Prairie View A&M University, Prairie View 77446, TX, USA; Corresponding author.College of Agriculture, Food, and Natural Resources, Prairie View A&M University, Prairie View 77446, TX, USACREDIT Center and Electrical and Computer Engineering Department, Prairie View A&M University, Prairie View 77446, TX, USACREDIT Center and Electrical and Computer Engineering Department, Prairie View A&M University, Prairie View 77446, TX, USAIn this study, we examined plant health prediction through the Normalized Difference Vegetation Index (NDVI) calculated from satellite image derived reflectance values in the near-infrared and red spectra. The problem is formulated as a temporal data prediction problem. Using MODIS/Terra Vegetation Indices 16-Day L3 Global 250 m SIN Grid V061 dataset, we designed and implemented Reservoir Computing (RC) models and transformer-based models including pretrained language model, and compared the prediction performance of these models to traditional machine learning and deep learning methods such as Nonlinear Regression, Decision Tree, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) network, and DLinear. It is observed that the DLinear/LSTM model showed exceptional predictive accuracy, while the pretrained RC model significantly enhanced traditional RC model forecasts. Additionally, Frozen Pretrained Transformer (FPT), a pretrained language model, showed superior performance in predicting specific NDVI values (most often peak or lowest NDVI), suggesting its effectiveness in precise temporal predictions. Furthermore, transformer-based models, specifically PatchTST and FPT, demonstrated substantial mean squared error reductions, particularly in limited data scenarios (1 %, 5 %, 15 % and 50 % sample sizes), indicating their robustness in precise NDVI temporal predictions when data is limited. The findings in this study demonstrated the effectiveness of emerging machine learning techniques such as reservoir computing and pretrained language model for remote sensing and their contributions in precision agriculture.http://www.sciencedirect.com/science/article/pii/S2589721724000539Temporal predictionNDVIDeep learning (DL)Reservoir computing (RC)Large language model (LLM)GPT2 |
spellingShingle | John Olamofe Ram Ray Xishuang Dong Lijun Qian Normalized difference vegetation index prediction using reservoir computing and pretrained language models Artificial Intelligence in Agriculture Temporal prediction NDVI Deep learning (DL) Reservoir computing (RC) Large language model (LLM) GPT2 |
title | Normalized difference vegetation index prediction using reservoir computing and pretrained language models |
title_full | Normalized difference vegetation index prediction using reservoir computing and pretrained language models |
title_fullStr | Normalized difference vegetation index prediction using reservoir computing and pretrained language models |
title_full_unstemmed | Normalized difference vegetation index prediction using reservoir computing and pretrained language models |
title_short | Normalized difference vegetation index prediction using reservoir computing and pretrained language models |
title_sort | normalized difference vegetation index prediction using reservoir computing and pretrained language models |
topic | Temporal prediction NDVI Deep learning (DL) Reservoir computing (RC) Large language model (LLM) GPT2 |
url | http://www.sciencedirect.com/science/article/pii/S2589721724000539 |
work_keys_str_mv | AT johnolamofe normalizeddifferencevegetationindexpredictionusingreservoircomputingandpretrainedlanguagemodels AT ramray normalizeddifferencevegetationindexpredictionusingreservoircomputingandpretrainedlanguagemodels AT xishuangdong normalizeddifferencevegetationindexpredictionusingreservoircomputingandpretrainedlanguagemodels AT lijunqian normalizeddifferencevegetationindexpredictionusingreservoircomputingandpretrainedlanguagemodels |