Enhancing Corn Yield Prediction in Iowa: A Concatenate-Based 2D-CNN-BILSTM Model with Integration of Sentinel-1/2 and SoilGRIDs Data DOI Creative Commons
Mahdiyeh Fathi,

Reza Shah-Hosseini,

Armin Moghimi

et al.

Published: Nov. 6, 2023

Ensuring food security in precision agriculture demands early prediction of corn yield the USA at international, regional, and local levels. Accurate estimation can play a crucial role averting famine by offering insights into availability during growing season. To address this, we propose Concatenate-based 2D-CNN-BILSTM model that integrates Sentinel-1, Sentinel-2, Soil GRIDS (global gridded soil information) data for Iowa State from 2018 to 2021. This approach utilizes Sentinel-2 features, including spectral bands (Blue, Green, Red, Red Edge 1/2/3, NIR, n-NIR, SWIR 1/2), vegetation indices (NDVI, LSWI, DVI, RVI, WDRVI, SAVI, VARIGREEN, GNDVI), alongside Sentinel 1 features (VV, VH, difference VV, RVI), (Silt, Clay, Sand, CEC, pH) as initial inputs. extract high-level this each month, dedicated 2D-CNN was designed. concatenates previous month with low-level subsequent serving input model. Additionally, incorporate single-time another implemented. Finally, soil, were concatenated fed BILSTM layer accurate prediction. Comparative analysis against random forest (RF), 2D-CNN, models, using metrics like RMSE, MAE, MAPE, Index Agreement, revealed superiority our It achieved an Agreement 84.67% RMSE 0.698 t/ha. The also performed well 0.799 t/ha 72.71%. followed closely 0.834 69.90%. In contrast, RF lagged 1.073 69.60%. Integration 1–2 Soil-GRIDs significantly improved accuracy. Combining reduced 16 kg increased 2.59%. study highlighted potential advanced machine learning (ML)/deep (DL) models achieving precise reliable predictions, which could support sustainable agricultural practices food-security initiatives.

Language: Английский

Estimation of winter canola growth parameter from UAV multi-angular spectral-texture information using stacking-based ensemble learning model DOI
Ruiqi Du, Junsheng Lu, Youzhen Xiang

et al.

Computers and Electronics in Agriculture, Journal Year: 2024, Volume and Issue: 222, P. 109074 - 109074

Published: May 23, 2024

Language: Английский

Citations

13
Artificial Intelligence Techniques in Crop Yield Estimation Based on Sentinel-2 Data: A Comprehensive Survey DOI Open Access
Muhammet Fatih Aslan, Kadir Sabancı, Busra Aslan

et al.

Sustainability, Journal Year: 2024, Volume and Issue: 16(18), P. 8277 - 8277

Published: Sept. 23, 2024

This review explores the integration of Artificial Intelligence (AI) with Sentinel-2 satellite data in context precision agriculture, specifically for crop yield estimation. The rapid advancements remote sensing technology, particularly through Sentinel-2’s high-resolution multispectral imagery, have transformed agricultural monitoring by providing critical on plant health, soil moisture, and growth patterns. By leveraging Vegetation Indices (VIs) derived from these images, AI algorithms, including Machine Learning (ML) Deep (DL) models, can now predict yields high accuracy. paper reviews studies past five years that utilize techniques to estimate crops like wheat, maize, rice, others. Various approaches are discussed, Random Forests, Support Vector Machines (SVM), Convolutional Neural Networks (CNNs), ensemble methods, all contributing refined forecasts. identifies a notable gap standardization methodologies, researchers using different VIs similar crops, leading varied results. As such, this study emphasizes need comprehensive comparisons more consistent methodologies future research. work underscores significant role advancing offering valuable insights aim enhance sustainability efficiency management advanced predictive models.

Language: Английский

Citations

10
Leveraging Remote Sensing Data for Yield Prediction with Deep Transfer Learning DOI Creative Commons
Florian Huber, Alvin Inderka, Volker Steinhage

et al.

Sensors, Journal Year: 2024, Volume and Issue: 24(3), P. 770 - 770

Published: Jan. 24, 2024

Remote sensing data represent one of the most important sources for automized yield prediction. High temporal and spatial resolution, historical record availability, reliability, low cost are key factors in predicting yields around world. Yield prediction as a machine learning task is challenging, reliable ground truth difficult to obtain, especially since new points can only be acquired once year during harvest. Factors that influence annual plentiful, acquisition expensive, crop-related often need captured by experts or specialized sensors. A solution both problems provided deep transfer based on remote data. Satellite images free charge, allows recognition yield-related patterns within countries where plentiful transfers knowledge other domains, thus limiting number observations needed. Within this study, we examine use prediction, preprocessing towards histograms unique. We present framework demonstrate its successful application gained from US soybean Argentina. perform alignment two domains improve applying several techniques, such L2-SP, BSS, layer freezing, overcome catastrophic forgetting negative problems. Lastly, exploit spatio-temporal Gaussian process. able performance Argentina total 19% terms RMSE 39% R2 compared predictions without processes. This proof concept advanced techniques form enable emerging developing countries, usually limited.

Language: Английский

Citations

9
Advancements in Utilizing Image-Analysis Technology for Crop-Yield Estimation DOI Creative Commons
Yu Feng, Ming Wang, Jun Xiao

et al.

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(6), P. 1003 - 1003

Published: March 12, 2024

Yield calculation is an important link in modern precision agriculture that effective means to improve breeding efficiency and adjust planting marketing plans. With the continuous progress of artificial intelligence sensing technology, yield-calculation schemes based on image-processing technology have many advantages such as high accuracy, low cost, non-destructive calculation, they been favored by a large number researchers. This article reviews research crop-yield remote images visible light images, describes technical characteristics applicable objects different schemes, focuses detailed explanations data acquisition, independent variable screening, algorithm selection, optimization. Common issues are also discussed summarized. Finally, solutions proposed for main problems arisen so far, future directions predicted, with aim achieving more wider popularization image technology.

Language: Английский

Citations

9
Garlic yield monitoring using vegetation indices and texture features derived from UAV multispectral imagery DOI Creative Commons
Andrea Marcone, Giorgio Impollonia, Michele Croci

et al.

Smart Agricultural Technology, Journal Year: 2024, Volume and Issue: 8, P. 100513 - 100513

Published: July 23, 2024

Remote sensing and machine learning are widely used to estimate crop yield. The use of these technologies for yield estimation bulbous vegetables is challenging because the underground can't be directly monitored by remote images. Among vegetables, garlic (Allium sativum L.) one most cultivated in world. aim this study was develop an accurate transferable model monitor using unmanned aerial vehicle (UAV) multispectral Data were collected over three growing seasons (2021, 2022, 2023) at four different phenological phases (202, 405, 407, 409 BBCH). random forest (RF) algorithm comparing two training feature sets: vegetation indices (VIs) VIs with addition texture features extracted from UAV important selected recursive elimination algorithm. Two methods compared: a direct bulb indirect aboveground biomass as proxy. To evaluate transferability RF models, cross-validation strategies nested leave-one-fold-out (LOFOCV) leave-one-year-out (LOYOCV). best performance achieved LOFOCV strategy. Regarding models between years (i.e. LOYOCV), method showed higher than method. Finally, improved accuracy but general, their contribution poor. This demonstrated that can accurately estimated sensing, UAVs suitable tool provide rapid reliable support monitoring.

Language: Английский

Citations

9
The impact of spatiotemporal variability of environmental conditions on wheat yield forecasting using remote sensing data and machine learning DOI Creative Commons

Keltoum Khechba,

Mariana Belgiu, Ahmed Laamrani

et al.

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2025, Volume and Issue: 136, P. 104367 - 104367

Published: Jan. 11, 2025

Language: Английский

Citations

1
Analysis and forecasting of Australian rice yield using phenology-based aggregation of satellite and weather data DOI Creative Commons
James Brinkhoff, Allister Clarke, Brian W. Dunn

et al.

Agricultural and Forest Meteorology, Journal Year: 2024, Volume and Issue: 353, P. 110055 - 110055

Published: May 18, 2024

Rice yield depends on factors including variety, weather, field management, nutrient and water availability. We analyzed important drivers of variability at the scale, developed forecast models for crops in temperate irrigated rice growing region Australia. fused a time-series Sentinel-1 Sentinel-2 satellite remote sensing imagery, spatial weather data management information. phenology was predicted using previously reported models. Higher yields were associated with early flowering, higher chlorophyll indices temperatures around flowering. Successive cropping same lower (p<0.001). After running series leave-one-year-out cross validation experiments, final trained 2018–2022 data, applied to predicting 1580 fields (43,700 hectares) from an independent season challenging conditions (2023). Models which aggregated phenological periods provided more accurate predictions than that these predictors calendar periods. The accuracy improved as progressed, reaching RMSE=1.6 t/ha Lin's concordance correlation coefficient (LCCC) 0.67 30 days after flowering level. Explainability SHAP method, revealing likely overall, individual fields.

Language: Английский

Citations

7
Improved feature ranking fusion process with Hybrid model for crop yield prediction DOI

Swanth Boppudi,

Sheela Jayachandran

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 93, P. 106121 - 106121

Published: March 6, 2024

Language: Английский

Citations

5
Soil salinization poses greater effects than soil moisture on field crop growth and yield in arid farming areas with intense irrigation DOI
Jingxiao Zhang, Jiabing Cai, Di Xu

et al.

Journal of Cleaner Production, Journal Year: 2024, Volume and Issue: 451, P. 142007 - 142007

Published: March 28, 2024

Language: Английский

Citations

5
Evaluating the efficiency of NDVI and climatic data in maize harvest prediction using machine learning DOI Creative Commons
Mario E. Suaza-Medina,

Jorge Laguna,

Rubén Béjar

et al.

International Journal of Digital Earth, Journal Year: 2024, Volume and Issue: 17(1)

Published: May 28, 2024

Accurate anticipation of the maize harvest date is important in agricultural market, as it ensures sustainability food production response to increasing global demand for food. This paper proposes a predictive model determine optimal time plots using Normalised Difference Vegetation Index (NDVI) and climatological data. These variables were oversampled used train various models, including Random Forest (RF), Gradient Boosting Machine (GBM), Light (LGBM), Extreme (XGBoost), CatBoost Support Vector (SVM). Bayesian optimisation has been find best hyperparameters Shapley values identify that exert most significant influence on prediction each instance. As result this approach, with an accuracy 92.1% Area Under Curve (AUC) 0.935 was developed. The determined these results atmospheric pressure, mean temperature, precipitation, NDVI, precipitation.

Language: Английский

Citations

4