Machine Learning Approach for Kharif Rice Yield Prediction Integrating Multi-Temporal Vegetation Indices and Weather and Non-Weather Variables

Chandra, Abhishek; Mitra, Pralay; Dubey, S. K.; Ray, Samrat

doi:10.5194/isprs-archives-xlii-3-w6-187-2019

Cited by 13 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the reasons is that combining and averaging multiple base models to produce the final prediction improves accuracy compared to single model alone [37]. Our findings are in line with other studies conducted by Chandra et al, [38] and Wen et al, [39], which show that random forest can be used to predict the yield. Phan et al, [40] reported that a random forest model was better than a support vector machine model at predicting tea yield using MODIS-NDVI with R-squared between 0.67-0.71.…”

Section: Discussionsupporting

confidence: 90%

Block-scale Oil Palm Yield Prediction Using Machine Learning Approaches Based on Landsat and MODIS Satellite Data

Yuhao Ang,

Helmi Zulhaidi Mohd Shafri,

Yang Ping Lee

et al. 2024

ARASET

View full text Add to dashboard Cite

Due to environmental threats and weather uncertainty concerns, oil palm yield prediction is crucial for sustaining crop production. This can be achieved through machine learning and utilising remotely sensed data to predict crop yield. However, the comparative studies on remotely sensed data in adopting the machine learning models are still limited due to the data accessibility. Therefore, we compare and evaluate the prediction accuracy between different satellites, namely MODIS and Landsat-7, using machine learning algorithms and the topology of deep neural networks. Random forest and stacking outperformed linear regression, ridge regression, and lasso regression for both Landsat-7 NDVI (R2= 0.78–0.80; RMSE=1.00- 1.26 tonnes per hectare; MAE=0.77- 0.79 tonnes per hectares; MAPE=0.03-0.04 tonnes per hectare) and MODIS NDVI (R2= 0.60–0.65 tonnes per hectares; RMSE= 2.72–2.81 tonne per hectares; MAE= 1.42-1.55, MAPE= 1.01- 1.02 tonnes per hectares). The Landsat-7 NDVI revealed that neural networks with a deeper network topology (R2= 0.85; RMSE= 1.42 tonnes per hectare; MAE=0.57 tonnes per hectares; MAPE=0.06 tonnes per hectare) outperformed neural networks with a baseline and broader network topologies in terms of performance. In contrast, MODIS-NDVI revealed that the neural network with a wider network topology had the highest overall prediction accuracy and the lowest prediction error (R2= 0.75; RMSE= 2.81 tonnes per hectare; MAE=2.27 tonnes per tonnes; MAPE= 0.13). Because of its higher spatial resolution in comparison to MODIS, landsat-7 NDVI used in neural networks with a deep network topology provided the best model performance. Although the use of NDVI as a single input factor may cause uncertainty in some extents, it is an efficient and reliable method for improving yield estimation with the use of medium-resolution satellites, which has important implications for early warning towards the reduction in yield production.

show abstract

Section: Discussionsupporting

confidence: 90%

Block-scale Oil Palm Yield Prediction Using Machine Learning Approaches Based on Landsat and MODIS Satellite Data

Yuhao Ang,

Helmi Zulhaidi Mohd Shafri,

Yang Ping Lee

et al. 2024

ARASET

View full text Add to dashboard Cite

show abstract

“…The analysis of the selected articles indicated that the studies differ with scale (ranging from field level to country level), ML algorithm (SVR, ANN, k-NN, GBR), platform (Sentinel, MODIS, LANDSAT), and crop (rice, wheat, sugarcane, arhar/tur). LANDSAT-8 satellite data with 30-meter resolution were effectively utilized for regional yield forecasting [69][70][71][72][73], followed by the images retrieved from MODIS [74][75][76]. Wolanin et al conducted wheat yield prediction in the Indo Gangetic Plains.…”

Section: Yield Predictionmentioning

confidence: 99%

Machine Learning-Driven Remote Sensing Applications for Agriculture in India—A Systematic Review

Pokhariyal,

Patel,

Govind

2023

Agronomy

View full text Add to dashboard Cite

In India, agriculture serves as the backbone of the economy, and is a primary source of employment. Despite the setbacks caused by the COVID-19 pandemic, the agriculture and allied sectors in India exhibited resilience, registered a growth of 3.4% during 2020–2121, even as the overall economic growth declined by 7.2% during the same period. The improvement of the agriculture sector holds paramount importance in sustaining the increasing population and safeguarding food security. Consequently, researchers worldwide have been concentrating on digitally transforming agriculture by leveraging advanced technologies to establish smart, sustainable, and lucrative farming systems. The advancement in remote sensing (RS) and machine learning (ML) has proven beneficial for farmers and policymakers in minimizing crop losses and optimizing resource utilization through valuable crop insights. In this paper, we present a comprehensive review of studies dedicated to the application of RS and ML in addressing agriculture-related challenges in India. We conducted a systematic literature review following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines and evaluated research articles published from 2015 to 2022. The objective of this study is to shed light on the application of both RS and ML technique across key agricultural domains, encompassing “crop management”, “soil management”, and “water management, ultimately leading to their improvement. This study primarily focuses on assessing the current status of using intelligent geospatial data analytics in Indian agriculture. Majority of the studies were carried out in the crop management category, where the deployment of various RS sensors led yielded substantial improvements in agricultural monitoring. The integration of remote sensing technology and machine learning techniques can enable an intelligent approach to agricultural monitoring, thereby providing valuable recommendations and insights for effective agricultural management.

show abstract

“…The cloud-free image with a nominal 8-day revisit frequency was used to calculate eight VIs that covered the range of currently representative VIs in crop yield estimation (Newton et al 2018;Chandra et al 2019;, including SR, WDRVI, NDVI, SAVI, MSAVI, GNDVI, GCVI and EVI (Table 2). Finally, we used entire time-series of VIs to average into the yearly state.…”

Section: Vismentioning

confidence: 99%

Oil Palm Yield Prediction Across Blocks Using Multi-Source Data and Machine Learning

Ang

Shafri

Lee³

et al. 2022

Preprint

View full text Add to dashboard Cite

Predicting yields on a bigger scale in a timely and accurate manner is essential for preventing climate risk and ensuring food security, particularly in the light of climate change and the escalation of extreme climatic events. Furthermore, crop yield estimates are affected by various factors including weather, nutrients and management practices. In this study, integrating multi-source data (i.e. satellite-derived vegetation indices (VIs), satellite-derived climatic variables (i.e. land surface temperature (LST) and rainfall precipitation, weather station and field-surveys), we built one multiple linear regression (MLR), three machine learnings (XGBoost, support vector regression, and random forest) and one deep learning (deep neural network) model to predict oil palm yield at block-level within the oil palm plantation. Moreover, time-series moving average and backward elimination feature selection techniques were implemented at the pre-processing stage. The yield prediction models were developed and tested using MLR, XGBoost, support vector regression (SVR), random forest (RF) and deep neural network (DNN) algorithms. Their model performances were then compared using evaluation metrics and generated the final spatial prediction map based on the best performance. DNN achieved the best model performances for both selected (R2=0.91; RMSE= 2.92 tonnes per ha; MAE= 2.56 tonnes per ha and MAPE= 0.09) and full predictors (R2=0.76; RMSE of 3.03 tonnes per ha; MAE of 2.88 tonnes per ha; MAPE of 0.10 tonnes per ha). In addition, advanced ensemble ML techniques such as XGBoost may be utilised as a supplementary for oil palm yield prediction at the block level. Among them, MLR recorded the lowest performance. By using backward elimination to identify the most significant predictors, the performance of all models was improved by 5% - 26% for R2, and that decreased by 3% - 31% for RMSE, 7% - 34% for MAE, and 1% - 15% for MAPE, respectively. DNN generates the most accurate statistical metrics, with an increase of around 15% for R2, 11% for RMSE, 32% for MAE and 1% for MAPE. Our study successfully developed efficient, effective and accurate yield prediction models for timely predicting oil palm yield over a large area by integrating data from multiple sources. These can be potentially handled by plantation management to estimate oil palm yields to speed up the decision-making process for sustainable production.

show abstract

Machine Learning Approach for Kharif Rice Yield Prediction Integrating Multi-Temporal Vegetation Indices and Weather and Non-Weather Variables

Cited by 13 publications

References 12 publications

Block-scale Oil Palm Yield Prediction Using Machine Learning Approaches Based on Landsat and MODIS Satellite Data

Block-scale Oil Palm Yield Prediction Using Machine Learning Approaches Based on Landsat and MODIS Satellite Data

Machine Learning-Driven Remote Sensing Applications for Agriculture in India—A Systematic Review

Oil Palm Yield Prediction Across Blocks Using Multi-Source Data and Machine Learning

Contact Info

Product

Resources

About