In both plant breeding and crop management, interpretability plays a crucial role in instilling trust in AI-driven approaches and enabling the provision of actionable insights. The primary objective of this research is to explore and evaluate the potential contributions of deep learning network architectures that employ stacked LSTM for end-of-season maize grain yield prediction. A secondary aim is to expand the capabilities of these networks by adapting them to better accommodate and leverage the multi-modality properties of remote sensing data. In this study, a multi-modal deep learning architecture that assimilates inputs from heterogeneous data streams, including high-resolution hyperspectral imagery, LiDAR point clouds, and environmental data, is proposed to forecast maize crop yields. The architecture includes attention mechanisms that assign varying levels of importance to different modalities and temporal features that, reflect the dynamics of plant growth and environmental interactions. The interpretability of the attention weights is investigated in multi-modal networks that seek to both improve predictions and attribute crop yield outcomes to genetic and environmental variables. This approach also contributes to increased interpretability of the model\'s predictions. The temporal attention weight distributions highlighted relevant factors and critical growth stages that contribute to the predictions. The results of this study affirm that the attention weights are consistent with recognized biological growth stages, thereby substantiating the network\'s capability to learn biologically interpretable features. Accuracies of the model\'s predictions of yield ranged from 0.82-0.93 R2 ref in this genetics-focused study, further highlighting the potential of attention-based models. Further, this research facilitates understanding of how multi-modality remote sensing aligns with the physiological stages of maize. The proposed architecture shows promise in improving predictions and offering interpretable insights into the factors affecting maize crop yields, while demonstrating the impact of data collection by different modalities through the growing season. By identifying relevant factors and critical growth stages, the model\'s attention weights provide valuable information that can be used in both plant breeding and crop management. The consistency of attention weights with biological growth stages reinforces the potential of deep learning networks in agricultural applications, particularly in leveraging remote sensing data for yield prediction. To the best of our knowledge, this is the first study that investigates the use of hyperspectral and LiDAR UAV time series data for explaining/interpreting plant growth stages within deep learning networks and forecasting plot-level maize grain yield using late fusion modalities with attention mechanisms.

In situ Electron Energy Loss Spectroscopy (EELS) combined with Transmission Electron Microscopy (TEM) has traditionally been pivotal for understanding how material processing choices affect local structure and composition. However, the ability to monitor and respond to ultrafast transient changes, now achievable with EELS and TEM, necessitates innovative analytical frameworks. Here, we introduce a machine learning (ML) framework tailored for the real-time assessment and characterization of in operando EELS Spectrum Images (EELS-SI). We focus on 2D MXenes as the sample material system, specifically targeting the understanding and control of their atomic-scale structural transformations that critically influence their electronic and optical properties. This approach requires fewer labeled training data points than typical deep learning classification methods. By integrating computationally generated structures of MXenes and experimental datasets into a unified latent space using Variational Autoencoders (VAE) in a unique training method, our framework accurately predicts structural evolutions at latencies pertinent to closed-loop processing within the TEM. This study presents a critical advancement in enabling automated, on-the-fly synthesis and characterization, significantly enhancing capabilities for materials discovery and the precision engineering of functional materials at the atomic scale.

Chlorophyll fluorescence (ChlF) parameters offer valuable insights into quantifying energy transfer and allocation at the photosystem level. However, tracking their variation based on reflectance spectral information remains challenging for large-scale remote sensing applications and ecological modeling. Spectral preprocessing methods, such as fractional-order derivatives (FODs), have been demonstrated to have advantages in highlighting spectral features. In this study, we developed and assessed the ability of novel spectral indices derived from FOD spectra and other spectral transformations to retrieve the ChlF parameters of various species and leaf groups. The results obtained showed that the empirical spectral indices were of low reliability in estimating the ChlF parameters. In contrast, the indices developed from low-order FOD spectra demonstrated a significant improvement in estimation. Furthermore, the incorporation of species specificity enhanced the tracking of the non-photochemical quenching (NPQ) of sunlit leaves (R2 = 0.61, r = 0.79, RMSE = 0.15, MAE = 0.13), the fraction of PSII open centers (qL) of shaded leaves (R2 = 0.50, r = 0.71, RMSE = 0.09, MAE = 0.08), and the fluorescence quantum yield (ΦF) of shaded leaves (R2 = 0.71, r = 0.85, RMSE = 0.002, MAE = 0.001). Our study demonstrates the potential of FOD spectra in capturing variations in ChlF parameters. Nevertheless, given the complexity and sensitivity of ChlF parameters, it is prudent to exercise caution when utilizing spectral indices for tracking them.

Hyperspectral imaging has emerged as an effective powerful tool in plentiful military, environmental, and civil applications over the last three decades. The modern remote sensing approaches are adequate for covering huge earth surfaces with phenomenal temporal, spectral, and spatial resolutions. These features make HSI more effective in various applications of remote sensing depending upon the physical estimation of identical material identification and manifold composite surfaces having accomplished spectral resolutions. Recently, HSI has attained immense significance in the research on safety and quality assessment of food, medical analysis, and agriculture applications. This review focuses on HSI fundamentals and its applications like safety and quality assessment of food, medical analysis, agriculture, water resources, plant stress identification, weed & crop discrimination, and flood management. Various investigators have promising solutions for automatic systems depending upon HSI. Future research may use this review as a baseline and future advancement analysis.

Hyperspectral detection of the change rate of organic matter content in agricultural remote sensing requires a high signal-to-noise ratio (SNR). However, due to the large number and efficiency limitation of the components, it is difficult to improve the SNR. This study uses high-efficiency convex grating with a diffraction efficiency exceeding 50% across the 360-850 nm range, a back-illuminated Complementary Metal Oxide Semiconductor (CMOS) detector with a 95% efficiency in peak wavelength, and silver-coated mirrors to develop an imaging spectrometer for detecting soil organic matter (SOM). The designed system meets the spectral resolution of 10 nm in the 360-850 nm range and achieves a swath of 100 km and a spatial resolution of 100 m at an orbital height of 648.2 km. This study also uses the basic structure of Offner with fewer components in the design and sets the mirrors of the Offner structure to have the same sphere, which can achieve the rapid adjustment of the co-standard. This study performs a theoretical analysis of the developed Offner imaging spectrometer based on the classical Rowland circular structure, with a 21.8 mm slit length; simulates its capacity for suppressing the +2nd-order diffraction stray light with the filter; and analyzes the imaging quality after meeting the tolerance requirements, which is combined with the surface shape characteristics of the high-efficiency grating. After this test, the grating has a diffraction efficiency above 50%, and the silver-coated mirrors have a reflection value above 95% on average. Finally, the laboratory tests show that the SNR over the waveband exceeds 300 and reaches 800 at 550 nm, which is higher than some current instruments in orbit for soil observation. The proposed imaging spectrometer has a spectral resolution of 10 nm, and its modulation transfer function (MTF) is greater than 0.23 at the Nyquist frequency, making it suitable for remote sensing observation of SOM change rate. The manufacture of such a high-efficiency broadband grating and the development of the proposed instrument with high energy transmission efficiency can provide a feasible technical solution for observing faint targets with a high SNR.

Retinal hyperspectral imaging (HSI) is a non-invasive in vivo approach that has shown promise in Alzheimer\'s disease. Parkinson\'s disease is another neurodegenerative disease where brain pathobiology such as alpha-synuclein and iron overaccumulation have been implicated in the retina. However, it remains unknown whether HSI is altered in in vivo models of Parkinson\'s disease, whether it differs from healthy aging, and the mechanisms which drive these changes. To address this, we conducted HSI in two mouse models of Parkinson\'s disease across different ages; an alpha-synuclein overaccumulation model (hA53T transgenic line M83, A53T) and an iron deposition model (Tau knock out, TauKO). In comparison to wild-type littermates the A53T and TauKO mice both demonstrated increased reflectivity at short wavelengths ~ 450 to 600 nm. In contrast, healthy aging in three background strains exhibited the opposite effect, a decreased reflectance in the short wavelength spectrum. We also demonstrate that the Parkinson\'s hyperspectral signature is similar to that from an Alzheimer\'s disease model, 5xFAD mice. Multivariate analyses of HSI were significant when plotted against age. Moreover, when alpha-synuclein, iron or retinal nerve fibre layer thickness were added as a cofactor this improved the R2 values of the correlations in certain groups. This study demonstrates an in vivo hyperspectral signature in Parkinson\'s disease that is consistent in two mouse models and is distinct from healthy aging. There is also a suggestion that factors including retinal deposition of alpha-synuclein and iron may play a role in driving the Parkinson\'s disease hyperspectral profile and retinal nerve fibre layer thickness in advanced aging. These findings suggest that HSI may be a promising translation tool in Parkinson\'s disease.

This study describes a novel method for grading pathological sections of gliomas. Our own integrated hyperspectral imaging system was employed to characterize 270 bands of cancerous tissue samples from microarray slides of gliomas. These samples were then classified according to the guidelines developed by the World Health Organization, which define the subtypes and grades of diffuse gliomas. We explored a hyperspectral feature extraction model called SMLMER-ResNet using microscopic hyperspectral images of brain gliomas of different malignancy grades. The model combines the channel attention mechanism and multi-scale image features to automatically learn the pathological organization of gliomas and obtain hierarchical feature representations, effectively removing the interference of redundant information. It also completes multi-modal, multi-scale spatial-spectral feature extraction to improve the automatic classification of glioma subtypes. The proposed classification method demonstrated high average classification accuracy (>97.3%) and a Kappa coefficient (0.954), indicating its effectiveness in improving the automatic classification of hyperspectral gliomas. The method is readily applicable in a wide range of clinical settings, offering valuable assistance in alleviating the workload of clinical pathologists. Furthermore, the study contributes to the development of more personalized and refined treatment plans, as well as subsequent follow-up and treatment adjustment, by providing physicians with insights into the underlying pathological organization of gliomas.

UNASSIGNED: The use of chemical fertilizers in rice field management directly affects rice yield. Traditional rice cultivation often relies on the experience of farmers to develop fertilization plans, which cannot be adjusted according to the fertilizer requirements of rice. At present, agricultural drones are widely used for early monitoring of rice, but due to their lack of rationality, they cannot directly guide fertilization. How to accurately apply nitrogen fertilizer during the tillering stage to stabilize rice yield is an urgent problem to be solved in the current large-scale rice production process.
UNASSIGNED: WOFOST is a highly mechanistic crop growth model that can effectively simulate the effects of fertilization on rice growth and development. However, due to its lack of spatial heterogeneity, its ability to simulate crop growth at the field level is weak. This study is based on UAV remote sensing to obtain hyperspectral data of rice canopy and assimilation with the WOFOST crop growth model, to study the decision-making method of nitrogen fertilizer application during the rice tillering stage. Extracting hyperspectral features of rice canopy using Continuous Projection Algorithm and constructing a hyperspectral inversion model for rice biomass based on Extreme Learning Machine. By using two data assimilation methods, Ensemble Kalman Filter and Four-Dimensional Variational, the inverted biomass of the rice biomass hyperspectral inversion model and the localized WOFOST crop growth model were assimilated, and the simulation results of the WOFOST model were corrected. With the average yield as the goal, use the WOFOST model to formulate fertilization decisions and create a fertilization prescription map to achieve precise fertilization during the tillering stage of rice.
UNASSIGNED: The research results indicate that the training set R2 and RMSE of the rice biomass hyperspectral inversion model are 0.953 and 0.076, respectively, while the testing set R2 and RMSE are 0.914 and 0.110, respectively. When obtaining the same yield, the fertilization strategy based on the ENKF assimilation method applied less fertilizer, reducing 5.9% compared to the standard fertilization scheme.
UNASSIGNED: This study enhances the rationality of unmanned aerial vehicle remote sensing machines through data assimilation, providing a new theoretical basis for the decision-making of rice fertilization.

This study examines the use of hyperspectral imaging for the identification of stale food items by analyzing minute changes in their spectral signatures. An algorithm is proposed for the detection of subtle alterations in spectral signatures and is validated through intra-class classification comparisons among various stages of adulterating food samples acquired using a spectroradiometer. The analysis reveals that the spectral angle mapper proves effective for inter-class classification of consumable food items but faces challenges in classifying slight changes in spectral signatures within the same category. In contrast, DNA encoding demonstrates reliability, despite the generated code-words being independent of the actual intensity of received reflectance at each band. DNA encoding can provide insights into the nature of absorbance or reflectance at each band, making it a valuable tool for intra-class classification. Additionally, a novel concept called spectral velocity is introduced for subclass pattern matching. This method of single-pixel analysis relies on artificially constructed nD-vectors derived from spectral signatures. The findings suggest that the combination of hyperspectral imaging and DNA encoding offers a valuable tool for the quality assurance of consumable food items and demonstrates its potential for ensuring food safety and quality, ultimately contributing to human health.

Leaf chlorophyll content (LCC) is an important physiological index to evaluate the photosynthetic capacity and growth health of crops. In this investigation, the focus was placed on the chlorophyll content per unit of leaf area (LCCA) and the chlorophyll content per unit of fresh weight (LCCW) during the tuber formation phase of potatoes in Northern Shaanxi. Ground-based hyperspectral data were acquired for this purpose to formulate the vegetation index. The correlation coefficient method was used to obtain the \"trilateral\" parameters with the best correlation between potato LCCA and LCCW, empirical vegetation index, any two-band vegetation index constructed after 0-2 fractional differential transformation (step size 0.5), and the parameters with the highest correlation among the three spectral parameters, which were divided into four combinations as model inputs. The prediction models of potato LCCA and LCCW were constructed using the support vector machine (SVM), random forest (RF) and back propagation neural network (BPNN) algorithms. The results showed that, compared with the \"trilateral\" parameter and the empirical vegetation index, the spectral index constructed by the hyperspectral reflectance after differential transformation had a stronger correlation with potato LCCA and LCCW. Compared with no treatment, the correlation between spectral index and potato LCC and the prediction accuracy of the model showed a trend of decreasing after initial growth with the increase in differential order. The highest correlation index after 0-2 order differential treatment is DI, and the maximum correlation coefficients are 0.787, 0.798, 0.792, 0.788 and 0.756, respectively. The maximum value of the spectral index correlation coefficient after each order differential treatment corresponds to the red edge or near-infrared band. A comprehensive comparison shows that in the LCCA and LCCW estimation models, the RF model has the highest accuracy when combination 3 is used as the input variable. Therefore, it is more recommended to use the LCCA to estimate the chlorophyll content of crop leaves in the agricultural practices of the potato industry. The results of this study can enhance the scientific understanding and accurate simulation of potato canopy spectral information, provide a theoretical basis for the remote sensing inversion of crop growth, and promote the development of modern precision agriculture.