Evaluation of statistical methods, remote sensing, and artificial intelligence in estimating biomass for assessing the potential of bioenergy production

Ghamari, Azhin; Zareei, Samira

doi:10.22034/jrenew.2026.244547

Evaluation of statistical methods, remote sensing, and artificial intelligence in estimating biomass for assessing the potential of bioenergy production

Document Type : Review Article

Authors

Azhin Ghamari

Samira Zareei

Department of Biosystems Engineering, Faculty of Agriculture, University of Kurdistan, Sanandaj, Iran

10.22034/jrenew.2026.244547

Abstract

Bioenergy is one of the important sources of renewable energy that has gained increasing attention due to the limitations of fossil fuel resources, as well as environmental pollution and greenhouse gas emissions resulting from the combustion of fossil fuels. Biomass, as the raw material for bioenergy production, is obtained from various sources such as plant residues, forestry, and agricultural products. By estimating the amount of biomass available in a given area, a suitable assessment of the potential for bioenergy production can be made. Satellite imagery is one of the best tools for estimating biomass quantities. In this study, various methods of analyzing satellite data, including remote sensing, Geographic Information Systems (GIS), Google Earth Engine (GEE), machine learning, artificial intelligence, and growth modeling, have been evaluated for biomass estimation. The results show that models based on vegetation indices have an accuracy of between 71 and 88%, while the combination of multi-satellite data increases the prediction accuracy to 96%, outperforming traditional methods by about 10%. In the field of machine learning, artificial neural networks (ANN) and deep neural networks (DNN) showed mapping accuracy of up to 90% and 97%, respectively. The random forest (RF) and support vector machine (SVM) algorithms provided an accuracy of between 70–90%. These findings indicate that the combination of satellite data with advanced technologies has the potential to provide more accurate and stable estimates of biomass.

Keywords

biofuels

biomass

machine learning

renewable energy

satellite imagery

Subjects

Renewable and New Energy

- مراجع

[1] M. H. Jorenush, S. Boroomand Nasab, A. A. Naseri, M. Pakparvar, S. Taghvaeian, Use of remote sensing indices in estimation of canopy cover, biomass and planting date of wheat, Iranian Journal of Irrigation and Drainage, vol. 14(1), pp. 193-204, 2020. (In Persian)

[2] H. Varvani, B. Farhadi Bansouleh, M. A. Sharifi, Assessment of Remote Sensing Based Vegetation Indices at Various Growth Stages for Estimation of Corn Biomass, Crop Production, vol. 11(3), pp. 29-41, 2019. (In Persian)

[3] C. B. Komaki, R. Asadikia, H. Niknahad Gharmakhar, Estimation of vegetation cover percentage and biomass using remote sensing indices (Case study: protected areas of Southern Alborz, Karaj), Journal of RS and GIS for Natural Resources, vol. 10(1), pp. 1-16, 2019. (In Persian)

[4] S. Sabaghzade, M. Zare, M. H. Mokhtari, Estimating Biomass using Landsat Satellite Images (Case study: Marak, Birjand), Journal of Range and Watershed Management, vol. 69(4), pp. 907-920, 2017. (In Persian)

[5] E. Abdali, M. J. Valadan Zoej, A. Taheri Dehkordi, E. Ghaderpour, A parallel-cascaded ensemble of machine learning models for crop type classification in Google Earth Engine using multi-temporal Sentinel-1/2 and Landsat-8/9 remote sensing data, Remote Sensing, vol. 16(1), 127, 2024.

[6] B. Kamkar, M. Dashtimarvili, H. Kazemi, Comparison of vegetation indices in estimating the residue biomass of spring and autumn crops (Watersheds in the southwest of Golestan province), Journal of Water and Soil Conversation, vol. 27(6), pp. 121-136, 2021. (In Persian)

[7] P. Sharma, L. Leigh, J. Chang, M. Maimaitijiang, M. Caffé, Above-ground biomass stimation in oats using UAV remote sensing and machine learning, Sensors, 22(2), vol. 601, 2022.

[8] Z. Shi, G. Ferrari, P. Ai, F. Marinello, A. Pezzuolo, Bioenergy potential from agricultural by-product in 2030: An AI-based spatial analysis and climate change scenarios in a Chinese region, Journal of Cleaner Production, vol. 436, 140621, 2024.

[9] S. A. Anees, K. Mehmood, W. R. Khan, M. Sajjad, T. A. Alahmadi, S. A, Alharbi, M. Luo, Integration of machine learning and remote sensing for above ground biomass estimation through Landsat-9 and field data in temperate forests of the Himalayan region, Ecological Informatics, vol. 82, 102732, 2024.

[10] Y. Shi, J. Gao, G. Brierley, X. Li, G. L. W. Perry, T. Xu, Improving the accuracy of models to map alpine grassland above-ground biomass using Google earth engine, Grass and Forage Science, vol. 78(2), 237–253, 2023.

[11] M. Zhang, X. Ma, A., Chen, J. Guo, X. Xing, D. Yang, B. Xu, X. Lan, X. Yang, A spatio-temporal fusion strategy for improving the estimation accuracy of the aboveground biomass in grassland based on GF-1 and MODIS, Ecological Indicators, vol. 157, 111276, 2023.

[12] Z. Liu, Y. Su, X. Xiao, Y. Qin, Y. Li, L. Liu,. Identification and mapping of yellow-flowering rapeseed fields by combining social media data, Sentinel-2 imagery, deep learning algorithm, and Google Earth Engine, International Journal of Applied Earth Observation and Geoinformation, vol. 132, 104047, 2024.

[13] K. Kang, Q. Yang, P. Bartocci, H. Wei, S. S. Liu, Z. Wu, H. Zhou, H. Yang, F. Fantozzi, H. Chen, Bioenergy in China: evaluation of domestic biomass resources and the associated greenhouse gas mitigation potentials, Renewable and Sustainable Energy Reviews, vol. 127, 109842, 2020.

[14] S. Xulu, N. Mbatha, K. Peerbhay, M. Gebreslasie, Detecting harvest events in plantation forest using Sentinel-1 and -2 data via Google Earth Engine, Forests, vol. 11(12), 1283, 2020.

[15] Y. Yao, H. Ren, Estimation of grassland aboveground biomass in northern China based on topography-climate-remote sensing data, Ecological Indicators, vol. 165, 112230, 2024.

[16] C. B. Pande, K. N. Moharir, S. K. Singh, A. M. A. Varade, S. F. R. Elbeltagi Khadri, P. Choudhari, Estimation of crop and forest biomass resources in a semi-arid region using satellite data and GIS, Journal of the Saudi Society of Agricultural Sciences, vol. 20(5), 302-311, 2021.

[17] Senocak, A.A., and Goren, H.G., 2022. “Forecasting the biomass-based energy potential using artificial intelligence and geographic information systems: A case study”. Engineering Science and Technology, an International Journal, 26, 100992.

[18] Servia, H., Pareeth, S., Michailovsky, C.I., de Fraiture, C., and Karimi, P., 2022. “Operational framework to predict field level crop biomass using remote sensing and data driven models”. International Journal of Applied Earth Observation and Geoinformation, 108, 102725.

[19] Vuorinne, I., Heiskanen, J., Maghenda, M., Mwangala, L., Muukkonen, P., and Pellikka, P.K.E., “Allometric models for estimating leaf biomass of sisal in a semi-arid environment in Kenya”. Biomass and Bioenergy, 155, 106294.

[20] Hu, P., Zheng, B., Chen, Q., Grunefeld, S., Choudhury, M.R., Fernandez, J., Potgieter, A., and Chapman, S.C., 2024. “Estimating aboveground biomass dynamics of wheat at small spatial scale by integrating crop growth and radiative transfer models with satellite remote sensing data”. Remote Sensing of Environment, 311, 114277.