Crop variety classification through hyperspectral imagery

July 5, 2023
Crop variety classification through hyperspectral imagery

Remote sensing imagery from satellites, aircraft, or ground-based sensors is pivotal in precision agriculture — a farming management practice that gathers, processes, and analyzes different data to determine inter and intra-field variability in crops. With precision agriculture, farmers have the ability to apply fertilizers, pesticides, tillage, and irrigation water more effectively and improve the crop yield without releasing excess contaminants into the environment.

Traditionally, spectral sensors have been used to capture images of crops over vast areas in specific wavelengths beyond the visible spectrum. However, these commercially-available sensors often lack the spectral quality required for identifying and quantifying small changes in plant physiology due to disease or environmental stress.

Hyperspectral imaging has shown the potential to shift how precision agriculture is managed. The high spectral resolution available on hyperspectral sensors can be utilized for crop variety classification to enable farmers to customize management practices, monitor health and growth and optimize input usage, costs, and yields.

What is variety classification?

Variety classification identifies and categorizes crop varieties based on unique characteristics such as genetic makeup, appearance, growth rate, yield potential, and resistance to pests/diseases. Crop varieties are diverse and abundant, with each possessing unique traits and characteristics. For example, Basmati, Jasmine, and Arborio are some different rice varieties.

Choosing the right crop variety is crucial in disease prevention and management since resistant varieties can minimize the need for chemical treatments and reduce disease risk. Variety selection also mitigates the impacts of extreme weather events like drought. For example, drought-tolerant maize varieties can produce approximately 30% of their potential yield after suffering water stress for six weeks before and during flowering and grain-filling.

Each crop variety emits a different spectral signature — a unique pattern of reflectance or absorption across wavelengths due to their inherent biochemical and physiological characteristics. One of the main reasons for their variation is due to pigments such as chlorophyll, which absorbs light in the blue and red parts of the spectrum and reflects green, giving plants their color.

The spectral signatures of seven rice varieties in the north of Iran. This study by Abbasi et al. (2010) analysed the red-edge position (i.e., the point of maximum slope between the red (visible) and near-infrared (NIR) reflectance regions) of the crops, which is an important indicator of chlorophyll and nitrogen concentrations.

Drought-tolerant crops exhibit different physiological and biochemical characteristics due to their ability to withstand water stress and nutrient deficiency and as a result, their spectral signatures vary as well.

Previous remote sensing techniques used in agriculture

So far, multispectral imaging has been used in agriculture to map and monitor vegetation growth and health. Multispectral images capture data across a few narrow wavelength bands, which can be used to derive vegetation indices like the Normalized Difference Vegetation Index, which measures plant health based on greenness and density.

However, multispectral imaging has limited capabilities beyond this point. Its sensor slack spectral resolution, making it unable to accurately identify crops due to limited sensitivity to subtle reflectance spectra variations. As a result, it is not ideal for crop variety identification or classification tasks.

This side-by-side comparison of a multispectral image (left) and a hyperspectral image (right) highlights the superior level of detail captured by hyperspectral imaging, showcasing the vast amount of information that can be obtained beyond what is possible with multispectral imaging.

How can hyperspectral imaging support variety classification?

Hyperspectral sensors capture data across hundreds of narrow wavelength bands, meaning they detect subtle differences in the spectral signatures of different crop varieties. On smaller scales, hyperspectral sensors can be mounted on vehicles for crop scanning during growth. However, the full potential of hyperspectral imaging is unlocked through remote sensing on satellites, enabling easy large-scale mapping of crop varieties across regions.

The ability to classify different varieties of crops based on these unique spectral signatures, influenced by chemical composition, pigmentation, water content, and environmental conditions with hyperspectral imaging satellites has wide-ranging applications in precision agriculture.

Hyperspectral imaging provides farmers with the toolkit to map, measure, analyze, and monitor their crops more accurately. This technology allows farmers to differentiate between different crop varieties, enabling the mapping of all varieties in fields and identifying areas requiring more or less inputs.

Hyperspectral imaging further allows for the quantification and analysis of variety performance by measuring parameters like chlorophyll and water content and disease symptoms, identifying thriving or struggling areas, optimizing planting strategies, and improving yields for increased profitability.

Consistent monitoring of crop health is also possible with hyperspectral imaging, allowing farmers to make timely and scientifically supported decisions about crop feasibility, inputs, and harvesting. Further, crop management practices, such as inventory control, insurance claims, and consultancy services can all benefit from accessing hyperspectral imaging over their croplands.

As the global population continues to grow, ensuring sustainable and efficient food production is critical. Advanced remote sensing technology, including Pixxel's hyperspectral imaging satellite sensors, offers a promising solution for precision farming practices, providing farmers with precise and reliable crop classification capabilities that can enhance their decision-making and contribute to more sustainable and productive farming practices.

Moreover, future advancements in remote sensing technology, including the development of new algorithms to detect minute variations in plant physiology, can further improve monitoring and management of agricultural resources, leading to more efficient and effective farming practices.

References :

Characterization of Maize Germplasm Grown in Eastern and Southern Africa: Results of the 2007Regional Trials Coordinated by CIMMYT. (2008). CIMMYT.

Abbasi, M. H., Darvishsefat, A. A., & Schaepman,  M. E. (2010). Spectral reflectance of rice canopies and red edge position (REP) as indicator of High yield varieties. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 1–5.