More Like this

1. Soil Carbon Estimation From Hyperspectral Imagery With Wavelet Decomposition and Frame Theory

   https://doi.org/10.1109/TGRS.2024.3461628  

   Roy, Bishal; Sagan, Vasit; Alifu, Haireti; Saxton, Jocelyn; Ghoreishi, Dorsa; Shakoor, Nadia (September 2024, IEEE Transactions on Geoscience and Remote Sensing)

   Assessing soil organic carbon (SOC) stocks is crucial for understanding the carbon sequestration potential of agroecosystems and for mitigating climate change. This study presents a novel method for assessing SOC and mineral content at various soil depths in sorghum crops using hyperspectral remote sensing. Conducted at Planthaven Farms, MO, the research encompassed ten genotypes across 30 plots, yielding 180 soil samples from six depth intervals (0–150 cm) of bare soil. Chemical analyses determined the SOC and mineral levels, which were then compared to spectral data from HySpex indoor sensors. We utilized time-frequency analysis methods, including discrete wavelet transformation (DWT), continuous wavelet transformation (CWT), and frame transformation along with traditional spectral transformations, specifically fractional derivatives and continuum removal. The analysis revealed the shortwave infrared (SWIR) region, particularly the 1800–2000 nm range, as having the strongest correlations with SOC content (with R2 exceeding 0.8). The visible near-infrared (VNIR) region also provided valuable insights. Models incorporating CWT achieved high accuracy (test R2 exceeding 0.9), while frame transformation achieved strong accuracy (test R2 between 0.7 and 0.8) with fewer features. The random forest regressor (RFR) proved to be most robust, demonstrating superior accuracy and reduced overfitting compared to support vector regression (SVR), partial least squares regression (PLSR), and deep neural network (DNN) models. The models demonstrated the efficacy of hyperspectral data for SOC estimation, suggesting potential for future applications that integrate this data with above-ground biomass to improve SOC mapping across larger scales. This research offers a promising spectral transformation approach for effective carbon management and sustainable agriculture in a changing climate. 

   more » « less
2. Hyperspectral imaging system for ice core studies

   https://doi.org/10.5194/egusphere-egu24-13878  

   Kurbatov, Andrei; Brook, Edward; Buizert, Christo; Carr, Theodore; Fegyveresi, John; Fudge, Tyler; Hargreaves, Geoffrey; Hoefen, Todd; Kirkpatrick, Liam; Labombard, Curtis; et al (March 2024, EGU General Assembly 2024)

   Hyperspectral imaging (HSI) technology has been increasingly used in Earth and planetary sciences. This imaging technique has been successfully tested on ice cores using VNIR (visible and near-infrared, 380-1000 nm) (Garzonio et al., 2018) and near-infrared (900 - 1700 nm) (McDowell et al, 2023)  line-scan cameras. Results show that  HSI data greatly expand ice core line-scan imaging capabilities, previously used with gray or RGB cameras (see summary in Dey et al., 2023). Combinations of selected HSI bands from the hyperspectral data cube improve feature detection in ice core stratigraphy, and map distribution of volcanic material, dust, air bubbles, fractures, and ice crystals in ice cores. Captured spectral information provides unique fingerprints for specific materials present in ice cores. This method helps to guide ice core sampling because it provides non-destructive, rapid visualization of microstructural properties, layering, bubble contents, increases in dust, or presence of  tephra material. Precise identification of these atmospheric components  is important for understanding past climate drivers reconstructed from ice cores. As part of the COLDEX project (Brook et al., this meeting) we adapted the SPECIM SisuSCS HSI system for ice core imaging. The ice core scanning system is housed inside the ca. -20ºC main NSF ICF freezer, and externally computer-controlled. The operator monitors scanning operations and communicates with personnel inside of the freezer via radio.  The system is equipped with a SPECIM FX10 camera that measures up to 224 bands in the VNIR range. We modified the ice core holder tray and installed a heated enclosure for the camera. The system uses SCHOTT DCR III Fiber Optic light sources with an OSL2BIR bulb from Thorlabs. IR filters are removed to extend the light spectral range beyond the 700 nm limit without heating the ice core surface during rapid (<5 minutes) scanning of an entire meter-long section. Emitted light enters ice at a 45º angle from two top and two bottom light sources. To calibrate absolute reflectance we use three Spectralon panels with 100, 50 and 20% reflectance values with every scan as well as several secondary reflective standards and USAF targets for geometric corrections. We are developing Python-based open source data processing routines and currently comparing HSI data with existing ice core physical and chemical measurements. The goal is to fully integrate the ice core HSI system with ice core processing at the NSF ICF. Dey et al., 2023. Application of Visual Stratigraphy from Line-Scan Images to Constrain Chronology and Melt Features of a Firn Core from Coastal Antarctica. Journal of Glaciology 69(273): 179–90. https://doi.org/10.1017/jog.2022.59.Garzonio et al., 2018. A Novel Hyperspectral System for High Resolution Imaging of Ice Cores: Application to Light-Absorbing Impurities and Ice Structure. Cold Regions Science and Technology 155: 47–57. https://doi.org/10.1016/j.coldregions.2018.07.005.McDowell et al., 2023. A Cold Laboratory Hyperspectral Imaging System to Map Grain Size and Ice Layer Distributions in Firn Cores. Preprint. Ice sheets/Instrumentation. https://doi.org/10.5194/egusphere-2023-2351. 

   more » « less
3. Differentiable Programming for Hyperspectral Unmixing using a Physics-based Dispersion Model

   Janiczek, John; Thaker, Parth; Dasarathy, Gautam; Edwards, Christopher; Christensen, Philip; Jayasuriya, Suren (January 2020, European Conference on Computer Vision (ECCV))

   Hyperspectral unmixing is an important remote sensing task with applications including material identification and analysis. Characteristic spectral features make many pure materials identifiable from their visible-to-infrared spectra, but quantifying their presence within a mixture is a challenging task due to nonlinearities and factors of variation. In this paper, spectral variation is considered from a physics-based approach and incorporated into an end-to-end spectral unmixing algorithm via differentiable programming. The dispersion model is introduced to simulate realistic spectral variation, and an efficient method to fit the parameters is presented. Then, this dispersion model is utilized as a generative model within an analysis-by-synthesis spectral unmixing algorithm. Further, a technique for inverse rendering using a convolutional neural network to predict parameters of the generative model is introduced to enhance performance and speed when training data is available. Results achieve state-of-the-art on both infrared and visible-to-near-infrared (VNIR) datasets, and show promise for the synergy between physicsbased models and deep learning in hyperspectral unmixing in the future. 

   more » « less
4. Hyperspectral Data Simulation (Sentinel-2 to AVIRIS-NG) for Improved Wildfire Fuel Mapping, Boreal Alaska

   https://doi.org/10.3390/rs13091693  

   Badola, Anushree; Panda, Santosh K.; Roberts, Dar A.; Waigl, Christine F.; Bhatt, Uma S.; Smith, Christopher W.; Jandt, Randi R. (May 2021, Remote Sensing)

   null (Ed.)

   Alaska has witnessed a significant increase in wildfire events in recent decades that have been linked to drier and warmer summers. Forest fuel maps play a vital role in wildfire management and risk assessment. Freely available multispectral datasets are widely used for land use and land cover mapping, but they have limited utility for fuel mapping due to their coarse spectral resolution. Hyperspectral datasets have a high spectral resolution, ideal for detailed fuel mapping, but they are limited and expensive to acquire. This study simulates hyperspectral data from Sentinel-2 multispectral data using the spectral response function of the Airborne Visible/Infrared Imaging Spectrometer-Next Generation (AVIRIS-NG) sensor, and normalized ground spectra of gravel, birch, and spruce. We used the Uniform Pattern Decomposition Method (UPDM) for spectral unmixing, which is a sensor-independent method, where each pixel is expressed as the linear sum of standard reference spectra. The simulated hyperspectral data have spectral characteristics of AVIRIS-NG and the reflectance properties of Sentinel-2 data. We validated the simulated spectra by visually and statistically comparing it with real AVIRIS-NG data. We observed a high correlation between the spectra of tree classes collected from AVIRIS-NG and simulated hyperspectral data. Upon performing species level classification, we achieved a classification accuracy of 89% for the simulated hyperspectral data, which is better than the accuracy of Sentinel-2 data (77.8%). We generated a fuel map from the simulated hyperspectral image using the Random Forest classifier. Our study demonstrated that low-cost and high-quality hyperspectral data can be generated from Sentinel-2 data using UPDM for improved land cover and vegetation mapping in the boreal forest. 

   more » « less
5. Fusion neural networks for plant classification: learning to combine RGB, hyperspectral, and lidar data

   https://doi.org/10.7717/peerj.11790  

   Scholl, Victoria M.; McGlinchy, Joseph; Price-Broncucia, Teo; Balch, Jennifer K.; Joseph, Maxwell B. (January 2021, PeerJ)

   Airborne remote sensing offers unprecedented opportunities to efficiently monitor vegetation, but methods to delineate and classify individual plant species using the collected data are still actively being developed and improved. The Integrating Data science with Trees and Remote Sensing (IDTReeS) plant identification competition openly invited scientists to create and compare individual tree mapping methods. Participants were tasked with training taxon identification algorithms based on two sites, to then transfer their methods to a third unseen site, using field-based plant observations in combination with airborne remote sensing image data products from the National Ecological Observatory Network (NEON). These data were captured by a high resolution digital camera sensitive to red, green, blue (RGB) light, hyperspectral imaging spectrometer spanning the visible to shortwave infrared wavelengths, and lidar systems to capture the spectral and structural properties of vegetation. As participants in the IDTReeS competition, we developed a two-stage deep learning approach to integrate NEON remote sensing data from all three sensors and classify individual plant species and genera. The first stage was a convolutional neural network that generates taxon probabilities from RGB images, and the second stage was a fusion neural network that “learns” how to combine these probabilities with hyperspectral and lidar data. Our two-stage approach leverages the ability of neural networks to flexibly and automatically extract descriptive features from complex image data with high dimensionality. Our method achieved an overall classification accuracy of 0.51 based on the training set, and 0.32 based on the test set which contained data from an unseen site with unknown taxa classes. Although transferability of classification algorithms to unseen sites with unknown species and genus classes proved to be a challenging task, developing methods with openly available NEON data that will be collected in a standardized format for 30 years allows for continual improvements and major gains for members of the computational ecology community. We outline promising directions related to data preparation and processing techniques for further investigation, and provide our code to contribute to open reproducible science efforts. 

   more » « less