article · Computers and Electronics in Agriculture
Advances in optical remote sensing and machine learning algorithms are improving the estimation of crop biophysical and biochemical parameters for precision farming. Developments have been propelled by new sensor availability, notably the freely accessible Sentinel-2 and the SuperDove constellation, which offer high spatial and temporal resolution alongside super-spectral configurations. Coupling radiative transfer models with machine learning regression algorithms, especially using red-edge bands, shows promise for operational crop stress monitoring to support agronomic decisions. However, models developed in Mediterranean climates perform poorly in African semi-arid regions and temperate continental climates in China. In Sub-Saharan Africa, remote sensing adoption faces hurdles including small field sizes, mixed cropping, and a lack of permanent experimental sites and systematic calibration data. Addressing these challenges requires locally calibrated or generic, transferable models that integrate crop-type mapping and spatio-temporal constraints for data-scarce settings.
Accurate tracking of crop health and growth allows farmers to make timely management decisions, improving agricultural productivity and resource efficiency. However, remote sensing tools optimised for specific regions cannot be directly applied globally. Understanding and resolving performance limitations in data-scarce regions like Sub-Saharan Africa is crucial for ensuring that precision agriculture technologies can benefit diverse farming environments and support food security.
These remote sensing approaches could enable commercial precision agriculture services and decision-support tools for agronomists, farm managers, and agribusinesses seeking to monitor crop health. While tools leveraging Sentinel-2 and SuperDove are technically operational in Mediterranean contexts, the technology remains early-stage or requires substantial adaptation for Sub-Saharan Africa. Commercial deployment in data-scarce regions depends on generating local calibration datasets and building models capable of handling small, mixed-crop fields.
AI-generated from the published abstract. Always read the original work before citing.
This paper provides an overview of the recent developments in remote sensing technology and machine learning algorithms for estimating important biophysical and biochemical parameters for precision farming. The objectives are (i) to provide an overview of recent advances in remotely sensed retrieval of biophysical and biochemical parameters brought by the developments in sensor technologies and robust machine learning algorithms and (ii) to identify the sources of uncertainty in retrieving biophysical and biochemical parameters and implications for precision agriculture. The review revealed that developments in crop biophysical and biochemical parameters retrieval techniques were mainly driven by announcements and the availability of new sensors. Two ground-breaking events can be identified, i.e., the availability of Sentinel-2 and the SuperDove constellation. The two provide high temporal-high spatial resolution data relevant for site-specific management and super-spectral configuration, enabling retrieval of crop growth and health parameters. The free availability of Sentinel-2 triggered the testing of its spectral configurations and upscaling of retrieval approaches using simulated data from field spectrometers and airborne hyperspectral sensors. SuperDoves will likely reduce the cost of very high-resolution data while providing unprecedented capabilities for detailed, accurate and frequent characterisation of field variability. Studies showed that the red-edge bands and hybrid models coupling Radiative Transfer Model (RTM) and machine learning regression algorithms (MLRA) are promising for operational and accurate monitoring of stress-related crop parameters to aid time-sensitive agronomic decisions. However, such models were tested in Mediterranean climates and performed poorly in African semi-arid areas and China’s temperate continental semi-humid monsoon climates. Therefore, locally-calibrated RTM models incorporating crop-type maps and other spatio-temporal constraints may reduce uncertainties when adapted to data-scarce regions. Generally, permanent experimental sites and a lack of systematic calibration data on various crops are some limiting factors to using remote sensing technologies for PA in Sub-Saharan Africa. Other complexities arise from farm configurations, such as small field sizes and mixed cropping practices. Therefore, future studies should develop generic, scalable and transferable models, especially within under-studied areas.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.compag.2024.108730
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
