A review of remote sensing-based crop yield estimation: machine learning techniques and environmental, algorithmic, and hardware limitations

Aman Muhammad; Abdul Sattar Mashori; Mansoor Jan; Ziqi Han; Fuzhong Li; Sanaullah Jan; Syed Aziz Shah

doi:10.3389/fpls.2026.1742689

A review of remote sensing-based crop yield estimation: machine learning techniques and environmental, algorithmic, and hardware limitations

Aman Muhammad
, Abdul Sattar Mashori
, Mansoor Jan
, Ziqi Han
, Fuzhong Li
, Sanaullah Jan
, Syed Aziz Shah

Centre for Healthcare and Community Transformation

Shanxi Agricultural University
Carlos III University of Madrid
Edinburgh Napier University

Research output: Contribution to journal › Review article › peer-review

9 Citations (Scopus)

99 Downloads (Pure)

Abstract

Advancements in agricultural technologies have increasingly emphasized technical innovations aimed at improving the predictability and reliability of agricultural outputs. These aspects encompass developments in agricultural machinery, automation technologies, biotechnology, and controlled environment farming systems. This article focuses on Remote Sensing (RS)-based approaches applied to agricultural yield estimation for both crops and plants. RS technologies offer enhanced precision and scalability, making them particularly effective for large-scale agricultural monitoring and analysis. A systematic classification of RS-based methodologies employed for crop yield estimation is presented in this study. These methodologies are categorized into: (i) Sensor-Based approaches, (ii) Platform-Based approaches, (iii) Analytical and Modeling-based methods, and (iv) Machine Learning (ML)-driven models. Based on findings reported across multiple studies, it is observed that Deep Learning (DL)-based architectures consistently achieve superior performance across key evaluation metrics, including accuracy, precision, recall, and F1-score. This performance advantage stems from their capacity to learn hierarchical representations, capture complex non-linear relationships, scale efficiently with large datasets, and reduce reliance on manual feature engineering. Following this classification, our article presents a comprehensive discussion of the limitations associated with these methodologies. These challenges are organized into four major categories: (i) Environmental, (ii) Algorithmic, (iii) Hardware and Operational, and (iv) Wireless Sensor Networks (WSNs) related limitations. The adopted classification framework helps readers identify and address the key challenges associated with effective yield estimation in crops and plants. Moreover, the article concludes by outlining several future research directions intended to support and guide both early-career and experienced researchers in this domain.

Original language	English
Article number	1742689
Number of pages	33
Journal	Frontiers in Plant Science
Volume	17
DOIs	https://doi.org/10.3389/fpls.2026.1742689
Publication status	Published - 19 Mar 2026

Bibliographical note

This is an open-access article distributed under the terms of the
Creative Commons Attribution License(CC BY). The use, distribution or
reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms

Funding

The author(s) declared that financial support was received for this work and/or its publication. This work was supported in part by the Research on Intelligent Decision Making System for Precision Agriculture 20220214060102, Key Research and Development Project of Shanxi Province; in part by Shanxi Provincial Oil Industry Technology, Institute of Economic Crops, Shanxi Agricultural University under Grant 2023CYJSTX05-17; in part by the Scientific and Technological Support for High Quality Development of Digital Monitoring and Intelligent Control Technology for Field Planting and Production, Special Project of Shanxi Agricultural University under Grant TYGC23-10; in part by the International Cooperation Project of State Administration of Foreign Experts Affairs (SAFEA). Integration and Application Demonstration of Key Technologies for Intelligent Operation of Agricultural Robots under Grant G2022004004L; in part by the Research on Block Chain Technology in the Brand Building and Protection of Special Agricultural Products, Shanxi Science and Technology Association under Grant 20210723; in part by the Postgraduate Teaching Reform and Practice Based on Virtual Laboratory, 2022 of Shanxi Agricultural University; in part by the Science and Technology Major Project of Shanxi Province, China 202202140601021 and in part by the College of Agricultural Engineering and Faculty of Software Technologies, Shanxi Agricultural University, Taigu Jinzhong, China.

Funders	Funder number
Shanxi Provincial Key Research and Development Project
State Administration of Foreign Experts Affairs
Shanxi Agricultural University	2023CYJSTX05-17, TYGC23-10
Shaanxi Science and Technology Association	20210723
Science and Technology Major Project of Shanxi Province	202202140601021

Keywords

limitations in yield estimation
remote sensing
crop productivity prediction and assessment
machine learning based yield estimation
wireless sensor networks based agriculture

Access to Document

10.3389/fpls.2026.1742689Licence: CC BY

Shah2026VoRFinal published version, 9.76 MBLicence: CC BY

Cite this

@article{28f82cbee4a94c639cc9d14dd8caee85,

title = "A review of remote sensing-based crop yield estimation: machine learning techniques and environmental, algorithmic, and hardware limitations",

abstract = "Advancements in agricultural technologies have increasingly emphasized technical innovations aimed at improving the predictability and reliability of agricultural outputs. These aspects encompass developments in agricultural machinery, automation technologies, biotechnology, and controlled environment farming systems. This article focuses on Remote Sensing (RS)-based approaches applied to agricultural yield estimation for both crops and plants. RS technologies offer enhanced precision and scalability, making them particularly effective for large-scale agricultural monitoring and analysis. A systematic classification of RS-based methodologies employed for crop yield estimation is presented in this study. These methodologies are categorized into: (i) Sensor-Based approaches, (ii) Platform-Based approaches, (iii) Analytical and Modeling-based methods, and (iv) Machine Learning (ML)-driven models. Based on findings reported across multiple studies, it is observed that Deep Learning (DL)-based architectures consistently achieve superior performance across key evaluation metrics, including accuracy, precision, recall, and F1-score. This performance advantage stems from their capacity to learn hierarchical representations, capture complex non-linear relationships, scale efficiently with large datasets, and reduce reliance on manual feature engineering. Following this classification, our article presents a comprehensive discussion of the limitations associated with these methodologies. These challenges are organized into four major categories: (i) Environmental, (ii) Algorithmic, (iii) Hardware and Operational, and (iv) Wireless Sensor Networks (WSNs) related limitations. The adopted classification framework helps readers identify and address the key challenges associated with effective yield estimation in crops and plants. Moreover, the article concludes by outlining several future research directions intended to support and guide both early-career and experienced researchers in this domain.",

keywords = "limitations in yield estimation, remote sensing, crop productivity prediction and assessment, machine learning based yield estimation, wireless sensor networks based agriculture",

author = "Aman Muhammad and Mashori, \{Abdul Sattar\} and Mansoor Jan and Ziqi Han and Fuzhong Li and Sanaullah Jan and Shah, \{Syed Aziz\}",

note = "This is an open-access article distributed under the terms of the Creative Commons Attribution License(CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms",

year = "2026",

month = mar,

day = "19",

doi = "10.3389/fpls.2026.1742689",

language = "English",

volume = "17",

journal = "Frontiers in Plant Science",

issn = "1664-462X",

publisher = "Frontiers Media S.A.",

}

TY - JOUR

T1 - A review of remote sensing-based crop yield estimation

T2 - machine learning techniques and environmental, algorithmic, and hardware limitations

AU - Muhammad, Aman

AU - Mashori, Abdul Sattar

AU - Jan, Mansoor

AU - Han, Ziqi

AU - Li, Fuzhong

AU - Jan, Sanaullah

AU - Shah, Syed Aziz

N1 - This is an open-access article distributed under the terms of the Creative Commons Attribution License(CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms

PY - 2026/3/19

Y1 - 2026/3/19

N2 - Advancements in agricultural technologies have increasingly emphasized technical innovations aimed at improving the predictability and reliability of agricultural outputs. These aspects encompass developments in agricultural machinery, automation technologies, biotechnology, and controlled environment farming systems. This article focuses on Remote Sensing (RS)-based approaches applied to agricultural yield estimation for both crops and plants. RS technologies offer enhanced precision and scalability, making them particularly effective for large-scale agricultural monitoring and analysis. A systematic classification of RS-based methodologies employed for crop yield estimation is presented in this study. These methodologies are categorized into: (i) Sensor-Based approaches, (ii) Platform-Based approaches, (iii) Analytical and Modeling-based methods, and (iv) Machine Learning (ML)-driven models. Based on findings reported across multiple studies, it is observed that Deep Learning (DL)-based architectures consistently achieve superior performance across key evaluation metrics, including accuracy, precision, recall, and F1-score. This performance advantage stems from their capacity to learn hierarchical representations, capture complex non-linear relationships, scale efficiently with large datasets, and reduce reliance on manual feature engineering. Following this classification, our article presents a comprehensive discussion of the limitations associated with these methodologies. These challenges are organized into four major categories: (i) Environmental, (ii) Algorithmic, (iii) Hardware and Operational, and (iv) Wireless Sensor Networks (WSNs) related limitations. The adopted classification framework helps readers identify and address the key challenges associated with effective yield estimation in crops and plants. Moreover, the article concludes by outlining several future research directions intended to support and guide both early-career and experienced researchers in this domain.

AB - Advancements in agricultural technologies have increasingly emphasized technical innovations aimed at improving the predictability and reliability of agricultural outputs. These aspects encompass developments in agricultural machinery, automation technologies, biotechnology, and controlled environment farming systems. This article focuses on Remote Sensing (RS)-based approaches applied to agricultural yield estimation for both crops and plants. RS technologies offer enhanced precision and scalability, making them particularly effective for large-scale agricultural monitoring and analysis. A systematic classification of RS-based methodologies employed for crop yield estimation is presented in this study. These methodologies are categorized into: (i) Sensor-Based approaches, (ii) Platform-Based approaches, (iii) Analytical and Modeling-based methods, and (iv) Machine Learning (ML)-driven models. Based on findings reported across multiple studies, it is observed that Deep Learning (DL)-based architectures consistently achieve superior performance across key evaluation metrics, including accuracy, precision, recall, and F1-score. This performance advantage stems from their capacity to learn hierarchical representations, capture complex non-linear relationships, scale efficiently with large datasets, and reduce reliance on manual feature engineering. Following this classification, our article presents a comprehensive discussion of the limitations associated with these methodologies. These challenges are organized into four major categories: (i) Environmental, (ii) Algorithmic, (iii) Hardware and Operational, and (iv) Wireless Sensor Networks (WSNs) related limitations. The adopted classification framework helps readers identify and address the key challenges associated with effective yield estimation in crops and plants. Moreover, the article concludes by outlining several future research directions intended to support and guide both early-career and experienced researchers in this domain.

KW - limitations in yield estimation

KW - remote sensing

KW - crop productivity prediction and assessment

KW - machine learning based yield estimation

KW - wireless sensor networks based agriculture

UR - https://www.scopus.com/pages/publications/105039159342

U2 - 10.3389/fpls.2026.1742689

DO - 10.3389/fpls.2026.1742689

M3 - Review article

SN - 1664-462X

VL - 17

JO - Frontiers in Plant Science

JF - Frontiers in Plant Science

M1 - 1742689

ER -

A review of remote sensing-based crop yield estimation: machine learning techniques and environmental, algorithmic, and hardware limitations

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this