Depth-resolved estimation of soil organic carbon (SOC) remains challenging because optical measurements originate at the surface while carbon dynamics vary vertically. We propose a physics-aware UAV framework that integrates multispectral (MSI) and hyperspectral (HSI) imagery to estimate SOC concentration (%) across five depths. The experiment was conducted at Plantheaven Farms, Missouri, with 10 sorghum genotypes across three replicates. Feature construction combined spectral derivatives from HSI with texture features from MSI, compressed via principal component analysis. Physics-based regularization was implemented through (i) a second-difference penalty to enforce vertical smoothness and (ii) a profile-integral consistency constraint to preserve whole-profile balance. Four model configurations evaluated on local data showed progressive improvements: MSI-only, MSI+HSI, MSI+HSI with smoothness, and MSI+HSI with full physics constraints. Additionally, transfer learning from the Open Soil Spectral Library (OSSL) was tested to address data limitations. Model fitting on the available data achieved R² = 0.72 at 0-30 cm, with physics-aware constraints notably improving vertical coherence. The physics-aware model reduced variance and improved plausibility. In-sample, transfer learning achieved R² = 0.60 at 0-30 cm, with conservative interpretation below 90 cm due to reduced optical sensitivity. Exploratory genotype patterns suggested higher surface SOC percent for PI 656029 and PI 656057, and lower values for PI 276837 and PI 656044.

Early detection and mitigation of crop pests like the Fall Armyworm is critical to ensuring food security, particularly for pest-sensitive crops such as maize and sorghum. Traditional monitoring approaches based on manual scouting or centralized analytics struggle to meet the high-precision real-time requirements of pest outbreaks, especially in remote and resource-constrained agricultural settings. In this paper, we present the design vision of AgriCane, a cyber-physical system (CPS) architecture that integrates legged robotic platforms, edge-native machine learning pipelines, and low-bandwidth communication to form a closed sensing-compute-actuation loop. Our vision is to have quadruped robots equipped with manipulators for fine-grained inspection under leaves and at soil level, performing lightweight, on-device detection and escalating uncertain cases to cloud-based models via compressed, opportunistic backhaul. This paper outlines the architectural pillars of AgriCane and identifies key open challenges across the communication, computing, and control stack, ranging from uncertainty-aware inference and real-time robotic control to hierarchical decision pipelines and adaptive scouting. Our goal is to foster cross-disciplinary discussion on the design of resilient, autonomous CPS for openfield agriculture.

Advancements in hyperspectral imaging technology open new avenues for Soil Organic Carbon (SOC) estimation, a critical factor in enhancing agricultural productivity and understanding carbon sequestration. This study analyzed 96 soil samples using the HySpex sensor system, covering visible and near-infrared (VNIR; 400-1000 nm over 700 spectral bands) and short-wave infrared (SWIR; 960-2500 nm over 362 spectral bands) spectrums. We integrated Discrete and Continuous Wavelet Transforms (DWT and CWT), applying Biorthogonal, Daubechies, Complex Morlet, Morlet, and Mexican hat wavelets for enhanced SOC detection. Our results indicate a marked improvement in SOC estimation, particularly with Complex Morlet and Mexican hat wavelets in CWT. Complementary chemical analysis validated the SOC levels. Depth-wise, the 15-30 cm range in the SWIR region showed the highest SOC correlation. We identified key spectral ranges, including 400-580 nm and 680-910 nm in VNIR, and 1150-2500 nm in SWIR, as strongly correlated with SOC, substantiated by lab analysis.

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$R^{2}$exceeding 0.8). The visible near-infrared (VNIR) region also provided valuable insights. Models incorporating CWT achieved high accuracy (test$R^{2}$exceeding 0.9), while frame transformation achieved strong accuracy (test$R^{2}$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.

Large scale field-phenotyping approaches have the potential to solve important questions about the relationship of plant genotype to plant phenotype. Computational approaches to measuring the phenotype (the observable plant features) are required to address the problem at a large scale, but machine learning approaches to extract phenotypes from sensor data have been hampered by limited access to (a) sufficiently large, organized multi-sensor datasets, (b) field trials that have a large scale and significant number of genotypes, (c) full genetic sequencing of those phenotypes, and (d) datasets sufficiently organized so that algorithm centered researchers can directly address the real biological problems. To address this, we present SGxP, a novel benchmark dataset from a large-scale field trial consisting of the complete genotype of over 300 sorghum varieties, and time sequences of imagery from several field plots growing each variety, taken with RGB and laser 3D scanner imaging. To lower the barrier to entry and facilitate further developments, we provide a set of well organized, multi-sensor imagery and corresponding genomic data. We implement baseline deep learning based phenotyping approaches to create baseline results for individual sensors and multi-sensor fusion for detecting genetic mutations with known impacts. We also provide and support an open-ended challenge by identifying thousands of genetic mutations whose phenotypic impacts are currently unknown. A web interface for machine learning researchers and practitioners to share approaches, visualizations and hypotheses supports engagement with plant biologists to further the understanding of the sorghum genotype x phenotype relationship. The full dataset, leaderboard (including baseline results) and discussion forums can be found at http://sorghumsnpbenchmark.com.

Near-earth hyperspectral big data present both huge opportunities and challenges for spurring developments in agriculture and high-throughput plant phenotyping and breeding. In this article, we present data-driven approaches to address the calibration challenges for utilizing near-earth hyperspectral data for agriculture. A data-driven, fully automated calibration workflow that includes a suite of robust algorithms for radiometric calibration, bidirectional reflectance distribution function (BRDF) correction and reflectance normalization, soil and shadow masking, and image quality assessments was developed. An empirical method that utilizes predetermined models between camera photon counts (digital numbers) and downwelling irradiance measurements for each spectral band was established to perform radiometric calibration. A kernel-driven semiempirical BRDF correction method based on the Ross Thick-Li Sparse (RTLS) model was used to normalize the data for both changes in solar elevation and sensor view angle differences attributed to pixel location within the field of view. Following rigorous radiometric and BRDF corrections, novel rule-based methods were developed to conduct automatic soil removal; and a newly proposed approach was used for image quality assessment; additionally, shadow masking and plot-level feature extraction were carried out. Our results show that the automated calibration, processing, storage, and analysis pipeline developed in this work can effectively handle massive amounts of hyperspectral data and address the urgent challenges related to the production of sustainable bioenergy and food crops, targeting methods to accelerate plant breeding for improving yield and biomass traits.