Integrating Satellite and Climate Data for Crop Yield Prediction: Spatiotemporal Analysis and Neural Network based Model
DOI:
https://doi.org/10.29304/jqcsm.2025.17.42559Keywords:
Artificial Neural Network,, Normalized Difference Vegetation Index,, Histogram learning Diwaniyah-Iraq.Abstract
In Diwaniyah-Iraq province, which its economy considerably depends on crop production, the accurate crop harvest prediction is an elementary requirement. The present study has faced some challenges represented as 1) scarce available agricultural data such as the complete absence of cropland maps and also fewer crop health and crop yields statistics; and 2) interannual variation in climatic factors in such semi-arid regions. To overcome these impediments, a novel methodology that concentrates on data fusion and Artificial Neural Networks (ANN) was proposed in this work. The time-series satellite-based Normalized Difference Vegetation Index (NDVI-MODIS) was integrated with a multi-source climate database, which showed extra and unique information across the whole season. The strong relation of NDVI with the time of the critical period of the crop growth and its sensitivity to the variability of yield during the growing season provides a powerful feature for prediction. Exploratory data analysis was applied to reveal the temporal patterns of correlations between fused data streams with crop yield. Artificial Neural Network (ANN) was used to construct a winter yield prediction model at the province level, due to the predictive capability of neural networks that come from the hierarchical/multi-layered structure. Several ANN models were tested on 18 years of data for Diwaniyah-Iraq province. Critically, the suggested model enables a reliable yield prediction nine weeks before wheat harvest and seven weeks before barley harvest. Through the testing phase, the best models achieved the results of R² > 0.9 for both wheat and barley, with 0.01<RMSE<0.1 for wheat and 0.06<RMSE<0.1 for barley. The proposed methodology presents a robust and generalizable framework for yield prediction in circumstances of data-scarce, semi-arid environments and small-scale cultivation areas, offering early decision-making and resource management tools across Iraq.
Downloads
References
P. Lucani and M. Saade, “Iraq Agriculture sector note,” (2012).
M. Burke and D. B. Lobell, “Satellite-based assessment of yield variation and its determinants in smallholder African systems,” Proc. Natl. Acad. Sci. U. S. A., vol. 114, no. 9, (2017), pp. 2189–2194, doi: 10.1073/pnas.1616919114.
A. R. Huete and H. Q. Liu, “An Error and Sensitivity Analysis of the Atmospheric and Soil-Correcting Variants of the NDVI for the MODISEOS,” IEEE Trans. Geosci. Remote Sens., vol. 32, no. 4, (1994), pp. 897–905, doi: 10.1109/36.298018.
A. Huete, K. Didan, T. Miura, E. P. Rodriguez, X. Gao, and L. G. Ferreira, “Overview of the radiometric and biophysical performance of the MODIS vegetation indices,” Remote Sens, vol. 83, no. Nov, (2002), pp. 195–213.
Z. H. Khalil and Abdullaev.S.M., “Sensitivity of Winter Crops to climate variability in the irrigated subtropics of Iraq (Al-Diwaniyah),” Procedia Comput. Sci., vol. 167, (2020), pp. 1066–1079, doi: DOI:10.1016/j.procs.2020.03.405.
S. Conradt, R. Bokusheva, R. Finger, and T. Kussaiynov, “Yield trend estimation in the presence of farm heterogeneity and non-linear technological change,” Q. J. Int. Agric., vol. 53, no. 2, (2014), pp. 121–140, doi: 10.22004/ag.econ.195732.
Ministry of Agriculture, “Iraqi Agrometeorological network.” [Online]. Available: https://agromet.gov.iq/en/
Ministry of Municipalities and Public Works, “Structural plan for Diwaniyah stage 5 report. Final report,” (2014).
“NASA MODIS Home Page.” [Online]. Available: https://modis.gsfc.nasa.gov/about/
Damien Sulla-Menashe and M. Friedl, “MCD12Q1 MODIS/Terra+Aqua Land Cover Type Yearly L3 Global 500m SIN Grid V006 [Data set],” NASA EOSDIS Land Processes DAAC. Accessed: Feb. 27, 2020. [Online]. Available: https://doi.org/10.5067/MODIS/MCD12Q1.006
D. Liang, Y. Zuo, L. Huang, J. Zhao, L. Teng, and F. Yang, “Evaluation of the Consistency of MODIS Land Cover Product (MCD12Q1) Based on Chinese 30 m GlobeLand30 Datasets: A Case Study in Anhui Province, China,” ISPRS Int. J. Geo-Information, vol. 4, no. 4, (2015), pp. 2519–2541, doi: 10.3390/ijgi4042519.
X. Xiao et al., “Mapping paddy rice agriculture in southern China using multi-temporal MODIS images,” Remote Sens. Environ., vol. 95, no. 4, (2005), pp. 480–492, doi: 10.1016/j.rse.2004.12.009.
R. S. Lunetta, J. F. Knight, J. Ediriwickrema, J. G. Lyon, and L. D. Worthy, “Land-cover change detection using multi-temporal MODIS NDVI data,” Remote Sens. Environ., vol. 105, no. 2, (2006), pp. 142–154, Nov., doi: 10.1016/j.rse.2006.06.018.
B. D. Wardlow, S. L. Egbert, and and J. H. Kastens, “Analysis of Time-Series MODIS 250 M Vegetation Index Data for Crop Classification in the U.S.”
K. Didan, “MOD13Q1 MODIS/Terra Vegetation Indices 16-Day L3 Global 250m SIN Grid V006.,” NASA EOSDIS L. Process. DAAC., 2015, doi: 10.5067/MODIS/MOD13Q1.006.
I. Harris, P. D. Jones, T. J. Osborn, and D. H. Lister, “Updated high-resolution grids of monthly climatic observations - the CRU TS3.10 Dataset,” Int. J. Climatol., vol. 34, no. 3, pp. 623–642, Mar. 2014, doi: 10.1002/joc.3711.
T. Stackhouse, P.W., Westberg, D., Hoell, J.M., Chandler, W.S. and Zhang, “Prediction of Worldwide Energy Resource (POWER)-Agroclimatology methodology-(1.0 latitude by 1.0 longitude spatial resolution).,” 2015, Hampton, NASA Langely Research Center. [Online]. Available: https://power.larc.nasa.gov/
P. M. Atkinson, “Super-Resolution Land Cover Classification Using the Two-Point Histogram,” geoENV IV — Geostatistics Environ. Appl., vol. 13, (2006), pp. 15–28, doi: 10.1007/1-4020-2115-1_2.
Y. Kita, “A study of change detection from satellite images using joint intensity histogram,” in 2008 19th International Conference on Pattern Recognition, IEEE, Dec. (2008), pp. 1–4. doi: 10.1109/ICPR.2008.4761020.
J. You, X. Li, M. Low, D. Lobell, and S. Ermon, “Deep Gaussian Process for Crop Yield Prediction Based on Remote Sensing Data,” in 31th AAAI Conference on Artificial Intelligence, Association for the Advancement of Artificial Intelligence, (2017), pp. 4559–4565.
H. Russello, “Convolutional Neural Networks for Crop Yield Prediction using Satellite Images,” IBM Center for Advanced Studies, (2018).
J. Sun, L. Di, Z. Sun, Y. Shen, and Z. Lai, “County-Level Soybean Yield Prediction Using Deep CNN-LSTM Model,” Sensors, vol. 19, no. 20, Oct. (2019), p. 4363, doi: 10.3390/s19204363.
W. W. Hsieh and B. Tang, “Applying Neural Network Models to Prediction and Data Analysis in Meteorology and Oceanography,” (1998). doi: 10.1175/1520-0477(1998)079<1855:ANNMTP>2.0.CO;2.
R. Kohavi, “A study of cross-validation and bootstrap for accuracy estimation and model,” in International Joint Conference on Artificial intelligence (IJCAI), (1995), pp. 1137–1143.
C. Tofallis, “A better measure of relative prediction accuracy for model selection and model estimation,” J. Oper. Res. Soc., vol. 66, no. 8, (2015), pp. 1352–1362, doi: 10.1057/jors.2014.103
J. Quille-Mamani, L. Ramos-Fernández , J. Huanuqueño-Murillo, D. Quispe-Tito, L. Cruz-Villacorta, E. Pino-Vargas, L. Flores del Pino, E. Heros-Aguilar, L. Ángel Ruiz, “Rice Yield Prediction Using Spectral and Textural Indices Derived from UAV Imagery and Machine Learning Models in Lambayeque, Peru”, Remote Sensing; 17(4):632, (2025), https://doi.org/10.3390/rs17040632.
A. Adin, E.T. Krainski, A. Lenzi, Z. Liu, J. Martínez-Minaya, and H. Rue, “Automatic cross-validation in structured models: Is it time to leave out leave-one-out?”, Spatial Statistics, 62, (2024), p.100843, https://doi.org/10.1016/j.spasta.2024.100843.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Zena H. Khalil
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
