Airborne and spaceborne remote sensing (RS) collecting hyperspectral imagery provides unprecedented opportunities for the detection and monitoring of floating riverine and marine plastic debris. However, a major challenge in the application of RS techniques is the lack of a fundamental understanding of spectral signatures of water-borne plastic debris. Recent work has emphasised the case for open-access hyperspectral reflectance reference libraries of commonly used polymer items. In this paper, we present and analyse a high-resolution hyperspectral image database of a unique mix of 40 virgin macroplastic items and vegetation. Our double camera setup covered the visible to shortwave infrared (VIS-SWIR) range from 400 to 1700 nm in a darkroom experiment with controlled illumination. The cameras scanned the samples floating in water and captured high-resolution images in 336 spectral bands. Using the resulting reflectance spectra of 1.89 million pixels in linear discriminant analyses (LDA), we determined the importance of each spectral band for discriminating between water and mixed floating debris, and vegetation and plastics. The absorption peaks of plastics (1215 nm, 1410 nm) and vegetation (710 nm, 1450 nm) are associated with high LDA weights. We then compared Sentinel-2 and Worldview-3 satellite bands with these outcomes and identified 12 satellite bands to overlap with important wavelengths for discrimination between the classes. Lastly, the Normalised Vegetation Difference Index (NDVI) and Floating Debris Index (FDI) were calculated to determine why they work, and how they could potentially be improved. These findings could be used to enhance existing efforts in monitoring macroplastic pollution, as well as form a baseline for the design of future multispectral RS systems.

Seaweed cultivation faces scalability challenges due to labor-intensive biomass monitoring. Here, we demonstrate a low cost RGB imaging system for Ulva spp. biomass estimation (0.5–5.0 g L ^{− 1} ) in land-based raceways. Using a generalized segmentation model, we extracted surface area and color (RGB, CIELAB) features as predictors for linear and log-linear regressions. Surface area proved the strongest predictor (R ² = 0.99, p = < 0.001, RMSE = 0.18 g L ^{− 1} ), with log-linear models outperforming linear regressions (R ² = 0.88, p = < 0.001, RMSE = 0.50 g L ^{− 1} ) in per revolution analysis. In validation under cross-device imaging conditions, the linear model produced more stable and less biased biomass estimates (mean error = 0.69–0.82 g L ^{− 1} ) than the log-linear model, despite shifts in sensor resolution and acquisition geometry. Aggregating frame-level data into three-minute revolutions reduced segmentation errors and accounted for random seaweed distribution, enabling accurate biomass density predictions. This accessible, scalable approach offers a practical solution to reduce labor costs and optimize yields in precision aquaculture.