The research, led by Alessandro Fabrizi of the University of Augsburg together with colleagues in Germany and Belgium, set out to answer a deceptively simple question: can optical remote sensing, which has proven effective for spotting floating plastic in oceans and rivers, also work over soil? The team combined laboratory-grade spectroscopy with drone-based imaging to build a foundation for monitoring macroplastic residues — fragments larger than five millimetres — left behind after agricultural plastic film use. Their findings carry practical weight, because these macroplastic fragments are believed to be a major source of secondary microplastics in farmland, slowly breaking down into particles that can alter soil physics, chemistry, and biology.

The first stage of the study took place on a rooftop in Louvain-la-Neuve, Belgium, where the researchers measured the reflectance of eight different low-density polyethylene films — the dominant material in agricultural covers — under natural sunlight. The films came in black, white, and transparent variants, including double-sided black-and-white films measured from both faces, effectively yielding ten film types. Each film was tested in four conditions: pristine, crumpled by hand, dirty from being rolled in soil, and both crumpled and dirty. Two contrasting soils, a silt loam from the Belgian loam belt and a standard sandy loam, served as backgrounds. Using a high-resolution spectroradiometer covering wavelengths from the visible into the short-wave infrared, the team captured 82 samples with five replicate measurements each, building one of the first open-access spectral libraries of agricultural plastic films.

The spectra revealed a striking pattern. White films reflected intensely in the visible range and faded gradually toward longer wavelengths; black films stayed dark and nearly featureless across the entire spectrum; and transparent films largely mimicked the reflectance of the soil beneath them, their signal shaped by thickness and additives. Crucially, the measurements pinpointed absorption features — narrow wavelength regions where plastic absorbs light — at roughly 1215, 1730, 1765, 2312, and 2352 nanometres, all in the short-wave infrared. These features are chemical fingerprints of the polymer itself, and the researchers showed that spectral indexes built around them could unambiguously separate plastic films from soils and crop residues, even when the films were coated with dirt. Notably, crumpling barely changed the films’ reflectance, while soil contamination mainly dampened brightness without erasing the diagnostic absorption features.

Armed with this spectral knowledge, the team moved to the field. On an agricultural plot near Córdoba in southern Spain, they laid out 53 pieces of film — 21 black, 19 transparent, and 13 white — each cut to roughly five by ten centimetres and pinned to the soil with metal spikes whose positions were recorded with centimetre-accurate satellite navigation. A drone flying at just seven metres above ground carried a five-band multispectral camera capturing blue, green, red, red edge, and near-infrared light, producing images with a ground resolution of about half a centimetre per pixel. The researchers then trained a random forest classifier to distinguish plastic pixels from bare soil, shadows, and other objects, testing four different data configurations that traded spectral richness against spatial detail.

The results delivered a surprise that challenges conventional wisdom in remote sensing. All three datasets flown at half-centimetre resolution — full multispectral, plain RGB, and RGB with added band ratios — performed similarly at detecting the known films, while a multispectral dataset degraded to 1.2-centimetre resolution missed many transparent films. In other words, for detecting fragments around five centimetres across, spatial resolution mattered as much as or more than spectral resolution. Because ordinary RGB cameras capture finer detail at a given flight height, or cover larger areas faster at the same detail, the authors conclude that high-resolution colour cameras should be favoured over multispectral sensors for mapping macroplastic film residues with today’s off-the-shelf technology. This is good news for practitioners: cheap, lightweight cameras on consumer drones could become a routine screening tool for farm-level plastic audits.

But the study also exposed sobering limitations. Although the classifier found most of the real films, it dramatically overestimated the total plastic cover — by a factor of roughly 21 to 44, depending on the dataset. The errors followed a colour-coded logic. Black films were confused with shadows cast by soil clods left by recent tillage; white films were confused with brightly reflecting patches of soil; and transparent films blended almost invisibly into the soil background in the visible and near-infrared bands. These confusions are not mere artefacts of a single field. Shadows and variable illumination are inherent to arable land, and transparent films genuinely lack distinguishing colour. The authors suggest practical countermeasures — flying under uniform conditions at high solar elevation, using multi-temporal flights, or building high-resolution surface models — but acknowledge that truly robust detection of transparent and black films will require seeing beyond the visible spectrum.

That is where the study points toward a technological gap with real consequences. The short-wave infrared absorption features that unambiguously identify plastic are found only on expensive hyperspectral instruments, which demand low flight altitudes, long survey times, and heavy data processing — a combination that rules out large-scale monitoring. Yet the researchers demonstrated that even a broadband index spanning the 1715-nanometre absorption region separated plastic from nearly everything else on cropland, with only a handful of rare minerals overlapping. This suggests that a purpose-built miniaturised multispectral camera carrying a few broad bands centred on plastic absorption features, alongside high-resolution visible bands, could deliver unambiguous detection at low cost and low data volume. Such a sensor, the authors argue, would be a milestone for monitoring plastic contamination on land, and could even distinguish polymer types: polyethylene, polypropylene, and PVC share similar features, but PET — the stuff of bottles and litter — absorbs at different wavelengths, potentially allowing managers to separate agricultural residues from dumped waste.

The timing of this work is significant. Regulatory limits on plastic concentrations in soil are beginning to emerge in Europe, and demand for fast, standardised monitoring is likely to follow. Because macroplastic fragments fragment into microplastics over time, reliable mapping of the larger residues would also sharpen risk assessments for soil ecosystems, where experiments have shown that high plastic loads can degrade soil properties and harm plants, even though the thresholds for damage remain poorly quantified. The Augsburg team’s spectral library is openly available, inviting other researchers to develop new indexes and detection algorithms on a shared foundation.

For now, the message to farmers, agronomists, and environmental agencies is pragmatic: a consumer drone with a good colour camera, flown carefully, can already map plastic film residues well enough to identify which fields, films, and management practices generate the most debris — knowledge that is essential for designing sustainable plasticulture. But the study’s deeper legacy may be its blueprint for the next generation of sensors. By showing exactly where plastic betrays itself in the spectrum, and exactly where current cameras fall short, the researchers have drawn a clear target for engineers: build small, affordable instruments that look at farmland not just in the colours we see, but in the infrared fingerprints that plastic cannot hide.

Subject of Research: Optical remote sensing of agricultural plastic film residues in cropland soils

Article Title: Plastic film residues on cropland: monitoring soil contamination through optical remote sensing

Article References: Fabrizi, A., Fiener, P., Van Oost, K., & Wilken, F. (2026). Plastic film residues on cropland: monitoring soil contamination through optical remote sensing. SOIL, 12(1), 715-731. https://doi.org/10.5194/soil-12-715-2026

Image Credits: AI Generated

DOI: 10.5194/soil-12-715-2026

Keywords: plastic pollution, agricultural soils, remote sensing, drones, UAV, multispectral imaging, hyperspectral, plastic film, mulching, microplastics, spectral library, soil contamination

The dataset, assembled by a team from the Silesian University of Technology, Opole University of Technology, AGH University of Kraków, KP Labs, QZ Solutions and the European Space Agency’s ϕ-Lab, contains 1,954 hyperspectral image patches covering more than 43,000 hectares of southern Poland. That translates to roughly 108 million labeled pixels, each carrying 430 spectral bands spanning the visible, near-infrared and short-wave infrared ranges from 414 to 2,357 nanometers. According to the authors, it is the largest and most heterogeneous collection of its kind for bare soil detection, and the first to provide pixel-level annotations for entire agricultural parcels rather than isolated, spatially unmoored pixels.

The imagery was acquired on 3 March 2021 under cloudless, windless skies, using a HySpex VS-725 system flown aboard a Piper PA-31 Navajo aircraft at altitudes between 2,550 and 2,700 meters. Two sensors worked in tandem: a VNIR-1800 capturing 186 bands at 3.26 nanometer resolution across 400 to 1,000 nanometers, and a SWIR-384 capturing 288 bands at 5.45 nanometer resolution across 930 to 2,500 nanometers. The resulting ground sampling distance of 2 meters is fine enough to resolve individual field boundaries, hedgerows and dirt tracks, which matters enormously when the goal is to delineate whole fields rather than rough statistical averages.

What makes HyBEAR genuinely novel is its labeling philosophy. Most existing collections treat bare soil detection as a pixel-by-pixel classification problem, which can mislead downstream applications. Fertilization planning, tillage monitoring and erosion assessment all operate at the level of entire fields, so what farmers and agronomists actually need is an algorithm that says: this parcel, as a whole, is free of vegetation. HyBEAR’s annotators therefore labeled complete parcels, applying a strict rule that a field qualified as SOIL only when at least roughly 85 percent of its surface showed visible bare ground with no signs of mature vegetation. Ambiguous cases were flagged as MAYBE-SOIL and resolved through consensus among three experts with one, four and ten years of remote sensing experience, with the most senior scientist arbitrating the hardest calls.

Getting those labels right was harder than it sounds. Vegetation indices such as NDVI, which flag chlorophyll activity, can miss sparse or freshly emerging plants, while roads, rooftops and artificial surfaces often show equally low index values and can be mistaken for soil. Plain RGB composites proved similarly treacherous, since bare earth, dirt roads and shadowed ground can look nearly identical depending on flight altitude and sun angle. The team combined automated index analysis with careful visual inspection of both natural-color and color-infrared renderings, explicitly excluding dirt roads, infrastructure, deep shadows near tree lines and areas where crop residues complicated the spectral signature. The result is a ground truth designed to survive contact with messy reality.

Heterogeneity was built in deliberately. The two source scenes, P1 near the village of Przeworno in Lower Silesia and P2 south of Głubczyce in the Opolskie region, lie more than 60 kilometers apart yet were flown within an hour of each other. Because the sun and clouds shifted between acquisitions, lighting and reflectance conditions differ measurably between the two areas, forcing any trained model to generalize rather than memorize. The 250-by-250-pixel patches were divided into five spatially disjoint folds, and the benchmark prescribes a five-fold cross-validation protocol in which each fold serves once as the test set. This design directly probes whether an algorithm tuned on one landscape can transfer its knowledge to another, a question that haunts every operational Earth observation system.

To give future researchers a starting line, the authors ran six classic machine learning models through the protocol: logistic regression, L2-regularized linear models, AdaBoost, linear-kernel support vector machines, decision trees and random forests, each operating on the full 430-dimensional spectral vector of every pixel. The results were revealing. Logistic regression and support vector machines led the pack, with average accuracy around 0.926 to 0.927 and F-scores approaching 0.9. More striking was what happened on Fold 0, the only fold drawn from the P1 scene. Non-linear models such as random forests, AdaBoost and decision trees, which had apparently overfitted the spectral character of the larger P2 scene, degraded sharply when tested across locations, while the simpler linear models held up. In machine learning, the humblest method winning is often the most instructive outcome.

The failure cases are as informative as the successes. Qualitative inspection of patches like IMG_0022_F0 shows that errors cluster around physical confounders: tree shadows that mimic dark soil, dirt roads that share its texture, and crop residues that spectrally mix with the underlying ground. Fold 0 also carries the lowest soil pixel ratio in the dataset, at 28.3 percent in the full version, compounding the difficulty. The authors argue that these weaknesses point toward deep learning approaches capable of learning spatial context and richer representations, rather than judging each pixel in isolation. They also note that the benchmark’s parcel-level annotations remain largely untapped by the current pixel-wise baselines, leaving a clear opening for field-level segmentation methods.

Beyond agriculture, HyBEAR has an unexpected role to play in spacecraft engineering. As hyperspectral instruments proliferate on satellites, the bottleneck is no longer acquisition but transmission and on-board computing. The authors describe bare soil detection as a form of smart data compression: by pruning everything that is not soil before downlink, a satellite can slash the volume of data it ships to the ground and reserve its limited memory and compute for pixels that actually matter. Extracting soil parameters from non-soil pixels would produce noisy, inherently incorrect estimates anyway, so filtering early is both an efficiency gain and an accuracy safeguard. Related work from the team, including in-orbit vegetation index detection on the Intuition-1 mission and even quantum-kernel support vector machines, suggests this pipeline is already moving toward flight hardware.

The benchmark ships with reproducibility baked in. Alongside the imagery and labels, the Zenodo release includes wavelength metadata for all 430 bands, Jupyter notebooks covering preprocessing, normalization and the full cross-validation logic, and the ten trained baseline models so that anyone can independently verify the reported numbers. The authors are candid about limitations: the data represents a single early-spring snapshot of one region, so global soil diversity and seasonal variation remain untested, and the evaluation primarily addresses regional rather than worldwide generalization. Future expansions are planned to bring in more geographic zones and timeframes. Even so, HyBEAR fills a gap the community has long acknowledged, replacing ad hoc comparisons with a shared yardstick, and giving the fast-growing field of AI-driven soil mapping something it has rarely had: a fair, expert-verified and genuinely difficult test.

Subject of Research: A large-scale hyperspectral benchmark dataset with expert-verified parcel-level annotations for bare soil detection in precision agriculture

Article Title: HyBEAR: a hyperspectral benchmark for bare soil detection

Article References: Wijata, A. M., Ruszczak, B., Niepala, A., Gumiela, M., Smykala, K., Longépé, N., & Nalepa, J. (2026). HyBEAR: a hyperspectral benchmark for bare soil detection. Earth System Science Data, 18(10), 7301-7317. https://doi.org/10.5194/essd-18-7301-2026

Image Credits: AI Generated

DOI: 10.5194/essd-18-7301-2026

Keywords: hyperspectral imaging, bare soil detection, precision agriculture, remote sensing, machine learning benchmark, Earth observation, soil mapping, cross-validation, satellite data compression, agricultural datasets, HyBEAR, hyperspectral

Conventional hyperspectral imaging requires capturing hundreds of narrow spectral bands, and doing so quickly and efficiently has long been a bottleneck in fields ranging from biomedical diagnostics to remote sensing and industrial inspection. Cameras and spectrometers must sweep through wavelengths or use complex filters, and the resulting data volume is enormous. The new approach sidesteps much of this burden by exploiting the fact that most natural scenes are highly compressible: instead of measuring every pixel at every wavelength, the system acquires a carefully chosen set of overlapping measurements and lets a neural network do the heavy lifting of reconstruction.

Ghost imaging, the conceptual foundation of the technique, has an unusual history. First demonstrated with entangled photon pairs in the mid-1990s, it relies on the correlation between two light beams: one that interacts with the object and is measured only by a bucket detector with no spatial resolution, and another that never touches the object but is fully resolved in space. By correlating the spatial patterns of the reference beam with the total intensities recorded by the bucket detector, an image of the object emerges—even though neither detector alone ever records a conventional picture. Over the past two decades, researchers have shown that ghost imaging can work with classical thermal light, with computational patterns generated by a spatial light modulator, and with far fewer measurements than traditional imaging would suggest, a strategy known as compressive ghost imaging.

The innovation reported in this study is the marriage of that compressive framework with dual-comb illumination. Dual-comb systems generate pairs of optical frequency combs—light sources whose spectra consist of thousands of evenly spaced, phase-coherent lines. When two combs with slightly different line spacings interfere, they produce a radio-frequency signal that maps the optical spectrum onto frequencies that ordinary electronics can measure. This elegant trick underlies dual-comb spectroscopy, which has transformed the precision with which chemists and physicists can interrogate molecular fingerprints, and it has won recognition across the optics community for enabling rapid, high-resolution spectral analysis without moving parts.

In the new scheme, the dual-comb source does double duty. It provides the spectral richness needed to probe the object across many wavelengths simultaneously, while the structured patterns encoded onto the illumination supply the spatial information that ghost imaging requires. Each bucket-detector measurement therefore contains a mixture of spatial and spectral information: the total light returned by the object for one particular structured pattern, summed over the full range of comb lines. No single measurement looks like an image, and no single measurement looks like a spectrum. Only in aggregate, across the entire set of acquisitions, does the information needed to reconstruct a full hyperspectral data cube exist.

Disentangling that mixture is where deep learning enters. The researchers trained a neural network to map the stack of raw bucket measurements—essentially a long list of intensity readings—onto the corresponding hyperspectral image. Because the network learns the statistical structure of natural hyperspectral scenes, it can fill in the gaps that compressive sampling leaves behind, resolving ambiguities that would defeat simpler reconstruction algorithms. Traditional compressed-sensing methods rely on iterative optimization with hand-designed sparsity constraints, which can be slow and brittle when measurements are scarce or noisy. A trained network, by contrast, performs the reconstruction in a single forward pass, making it dramatically faster and more robust in practice.

The team validated the approach in laboratory experiments, reconstructing hyperspectral images of test targets from measurement counts far below the nominal number of pixels times spectral channels that a conventional system would require. The reconstructions preserved fine spatial detail and accurate spectral profiles across the comb’s bandwidth, confirming that the dual-comb architecture delivers genuine spectral resolution rather than coarse color information. The authors report that the deep-learning reconstruction substantially outperformed baseline compressive-sensing algorithms at the same sampling ratios, producing cleaner images with fewer artifacts and better fidelity to the ground truth.

The implications extend well beyond the laboratory bench. Hyperspectral imaging has become an indispensable tool in agriculture, where it reveals plant stress and disease before they are visible to the eye; in food safety, where it detects contamination and ripeness non-destructively; in medicine, where tissue oxygenation and pathology produce subtle spectral signatures; and in environmental monitoring, where it tracks pollutants, algal blooms, and mineral distributions from aircraft and satellites. In all of these applications, acquisition speed and light budget are critical constraints. A technique that extracts full spectral-spatial information from a sparse set of measurements could enable hyperspectral video, imaging of light-sensitive biological samples, and deployment on platforms where size, weight, and power are severely limited.

Dual-comb technology itself has been maturing rapidly, with chip-scale microresonator combs now replacing bulky mode-locked lasers in many demonstrations. The integration of combs on photonic chips suggests that the imaging architecture demonstrated here could eventually shrink to a footprint compatible with drones, endoscopes, or handheld sensors. Combined with the computational reconstruction pipeline, which runs on conventional hardware once the network is trained, the system points toward hyperspectral imaging that is simultaneously fast, compact, and information-rich—a combination that no single existing modality offers.

The work also contributes to a broader conceptual shift in optical imaging. Rather than treating measurement and computation as separate stages, modern imaging systems increasingly co-design them: the illumination pattern, the detector configuration, and the reconstruction algorithm are optimized together to maximize the information extracted per photon. Ghost imaging, once considered a curiosity of quantum optics, has proven to be a flexible canvas for this philosophy. By adding spectral dimensions through dual-comb illumination and reconstruction intelligence through deep learning, the new study illustrates how far that co-design approach can go—capturing data cubes that no camera could record directly, from measurements that no camera would ever make.

Challenges remain before the technique reaches routine use. Training the reconstruction network requires representative datasets, and performance can degrade when the imaged scenes stray far from the training distribution. The dual-comb source must maintain phase coherence and stability across the full spectral band, and the measurement time scales with the number of structured patterns projected onto the object. The researchers note, however, that the compressive framework is inherently compatible with faster spatial light modulators, single-pixel detectors with higher sensitivity, and more sophisticated network architectures, leaving substantial room for improvement on every axis of the system.

For now, the demonstration stands as a striking example of how combining mature optical technologies in unexpected ways can unlock new measurement capabilities. Ghost imaging supplies the measurement economy, dual combs supply the spectral precision, and deep learning supplies the interpretive power—three ingredients that, woven together, turn a stream of seemingly meaningless detector clicks into vivid, wavelength-resolved pictures of the world.

Subject of Research: Hyperspectral dual-comb compressive ghost imaging with deep-learning-based image reconstruction

Article Title: Hyperspectral dual-comb compressive ghost imaging with deep learning reconstruction

Article References: Suh, M.-G., Dang, D., Gao, M., Jin, Y., Shin, D.-C., Gupta, A., Park, B. J., Uzundal, C., Hu, B., Kort-Kamp, W. J. M., & Lee, H. W. H. (2026). Hyperspectral dual-comb compressive ghost imaging with deep learning reconstruction. Light: Science & Applications, 15(1), Article 380. https://doi.org/10.1038/s41377-026-02417-z

Image Credits: AI Generated

DOI: 10.1038/s41377-026-02417-z

Keywords: hyperspectral imaging, ghost imaging, dual-comb spectroscopy, deep learning, compressive sensing, optical frequency combs, single-pixel imaging, neural network reconstruction, computational imaging, Light Science & Applications, Hyperspectral, dual-comb