Combination Bands Research Articles

An adaptive evolutionary-reinforcement learning algorithm for hyperspectral band selection

Band selection is one of the most important considerations for hyperspectral imaging (HSI) datasets that involves selecting fewer bands with higher classification accuracy. As a combinatorial optimization problem, evolutionary algorithm has been applied in the field, but the optimization ability and number of selected bands are limited with the control of exploration and exploitation. In this paper, an adaptive evolutionary-reinforcement learning algorithm (ERLA) is proposed for band selection of HSI datasets, only a suitable phase contributes to updating the corresponding agents in each iteration, and the coding length is adaptively lessened with the potential solution space. In addition, reinforcement learning is used to choose a feasible action in each iteration, and the unselected bands are removed from the candidate band combination in the previous state. A simulation study is conducted on four public HSI datasets, where the proposed framework has delivered an overall accuracy of 98% for 12% of bands in Chikusei dataset, 92% for 11% in KSC dataset, 93% against 19% for Xiongan dataset, and 97% in Longkou dataset with 10% bands retained, demonstrating that the proposed framework outperforms other approaches with several targets, and that the number of selected bands is obviously decreased with satisfactory classification accuracy.

Inversion of Soil Moisture Content in Cotton Fields Using GBR-RF Algorithm Combined with Sentinel-2 Satellite Spectral Data

Soil moisture content plays a vital role in agricultural production, significantly influencing crop growth, development, and yield. Thoroughly understanding the specific soil moisture content in cotton fields is crucial for enhancing agricultural efficiency and driving sustainable agricultural development. This study utilized the gradient-boosting regression–random forest (GBR-RF) algorithm and the GBR and RF algorithms separately, in conjunction with Sentinel-2 satellite images, to estimate cotton soil moisture content, focusing on the B1–B8 bands and in particular the sensitive B6, B7, and B8 bands. The soil data in the jujube orchard of the study area were collected using soil augers at a depth of 30 cm, with soil data collected from a depth of 20 to 30 cm. The findings revealed that the integrated learning algorithm GBR-RF demonstrated high accuracy, with R2, MAE, and MSE results of 0.8838, 1.0121, and 1.6168, respectively. In comparison, the results using just the GBR algorithm yielded R2, MAE, and MSE values of 0.8158, 1.1327, and 1.9645, respectively, while those obtained from the RF algorithm were 0.8415, 1.0680, and 1.8331, respectively. These results indicate that the algorithms exhibited strong generalization, robustness, and accuracy, with GBR-RF outperforming GBR and RF by 8.34% and 5.03%, respectively, in combination with using the B1–B8 bands for inversion. Furthermore, utilizing the full-band data resulted in R2 values that were up to 24.27% higher than those of the individual bands, affirming the efficacy of band combinations for improved accuracy. This study’s demonstration of the positive impact of integrated learning algorithms on estimating cotton soil moisture content underscores the advantages of multi-band data combinations over single-band data, highlighting their ability to enhance accuracy without significantly impacting errors. Importantly, this study’s findings, while not limited to a single experimental field, have broad applicability in cotton precision agriculture, offering valuable insights for research on yield enhancement and agricultural efficiency.

Remote cyanobacteria detection by multispectral drone imagery

Bartelt G, You J, Hondzo M. 2024. Remote cyanobacteria detection by multispectral drone imagery. Lake Reserv Manage. 40:236–247. Cyanobacteria play a crucial role in the ecological services of aquatic environments. Remote detection of cyanobacteria in water using satellite-based sensor images has been proven effective in monitoring eutrophication and harmful algal blooms. Satellite-based sensors are good at tracking large blooms in oceans and lakes, but not in small bodies of water. This study seeks to use remote-sensing techniques on images obtained from a multispectral camera mounted on an unmanned aerial system (UAS). We investigated a small freshwater lake, Brownie Lake, in Minneapolis, Minnesota, using the UAS. We compared the collected imagery to the measurements of chlorophyll and phycocyanin concentrations. Cyanobacterial chlorophyll a (Chl-a) concentrations and multispectral UAS data showed good agreement (r 2 = 0.54) in this study. Chl-a concentration strongly correlated with the presence of the near-infrared band at 840 nm and the red band at 668 nm. The most correlated spectral band combinations were the normalized difference vegetative index (NDVI) and 2 band algorithm (2BDA). Our research demonstrates the usefulness of UAS technologies in water quality monitoring.

Prediction of soil organic carbon in black soil based on a synergistic scheme from hyperspectral data: Combining fractional-order derivatives and three-dimensional spectral indices

Monitoring soil organic carbon (SOC) content is crucial for climate change mitigation and sustaining ecological balance. Despite the unparalleled advantages of hyperspectral data in capturing nuanced variations in soil properties through its high spectral resolution, effectively extracting useful features from numerous bands via spectral processing techniques remains a formidable challenge. This study proposes an integrated approach combining fractional-order derivative (FOD) technique and optimal band combination algorithm using ZY1-02D satellite hyperspectral data to estimate SOC in Northeast China’s Black soil region. Three modeling strategies were compared: (1) FOD-transformed reflectance (FOD spectra), (2) FOD spectra with traditional 2D spectral indices (FOD + 2D SI), and (3) FOD spectra with new 3D spectral indices (FOD + 3D SI). These strategies were implemented using the random forest model with the aim of the optimal SOC prediction. Results showed that the application of FOD technique for spectral transformation effectively addressed the challenges posed by overlapping peaks and baseline drift inherent in the original spectral reflectance. Additionally, FOD transformation enhanced subtle soil spectral features and yielded more pronounced spectral variations with increasing fractional order, as compared to the original spectral data and conventional integer-order derivatives (i.e., first and second-order derivatives). However, as the FOD order continued to increase beyond 1.4, the spectral curve exhibited amplified noise and distortion, thereby adversely impacting subsequent model development. The 3D spectral indices correlate more robustly with SOC than 2D indices. The model that combines 0.6-order FOD and 3D spectral indices achieved the best accuracy (R2 = 0.66, RMSE = 2.99 g/kg and MAE = 2.42 g/kg), significantly outperforming the models built by 0.6-order FOD spectra (R2 = 0.48, RMSE = 3.65 g kg−1, and MAE = 2.93 g kg−1) and 0.8-order FOD + 2D SI modeling strategy (R2 = 0.55, RMSE = 3.54 g kg−1, and MAE = 2.85 g kg−1). These findings indicated that FOD and 3D spectral indices exhibit superior synergistic performance in SOC prediction, demonstrating their feasibility and providing valuable insights for large-scale soil property prediction and mapping using satellite hyperspectral data.

Improving SSC detection accuracy of cherry tomatoes by feature synergy and complementary spectral bands combination

The visible/near-infrared (VIS/NIR) spectroscopy technique has been extensively employed for the non-destructive detection of soluble solids content (SSC) in fruit. However, some existing algorithms and modeling optimization methods for improving the detection accuracy of SSC may be applicable to specific conditions and not universal. To break through this bottleneck problem, we propose a potentially universal strategy based on feature synergy and spectral bands combination of multiple detection modes. Firstly, compared with the commonly used halogen lamp, the xenon lamp was utilized to cover the ultraviolet (UV) range and match the characteristic information of different sugars (glucose, fructose, and sucrose). Furthermore, the spectral fusion method was employed to combine the reflectance and transmittance spectra to improve the cherry tomatoes SSC prediction accuracy with comprehensive data in the UV/VIS/NIR region. Finally, the best results were achieved by the partial least square regression (PLSR) model with spectral bands fusion, yielding the results of R2p, RMSEP, and RPD as 0.9653, 0.1998%, and 5.31, respectively. The same conclusion can also be verified when predicting the SSC in strawberries. Overall, this strategy is potentially universal to improve the prediction accuracy of SSC in fruit by matching light source spectra with characteristic absorption, as well as utilizing comprehensive spectral information in the 200–1100 nm range, providing valuable insights for the practical application of nondestructive detection of fruit internal quality.

Selection of Spectral Parameters and Optimization of Estimation Models for Soil Total Nitrogen Content during Fertilization Period in Apple Orchards

The rapid and accurate diagnosis of nitrogen content in apple orchard soil is of great significance for the rational application of nitrogen fertilizer in orchards to improve apple yield and quality. An apple orchard in Shuangquan Town, Changqing District, Jinan City, Shandong Province, was taken as the experimental area. The optimal method for extracting spectral characteristic bands and screening spectral characteristic indices (SCIs) of soil total nitrogen (TN) for independent and comprehensive fertilization periods was explored. Independent and comprehensive soil TN content estimation models were constructed and optimized for each and the entire fertilization period, respectively. The results show that compared with the correlation coefficient method, stepwise multiple linear regression (SMLR) performs better in extracting hyperspectral characteristic bands of soil TN content. It helps to achieve a higher modeling accuracy, smaller root mean square error (RMSE), and is more conducive to avoiding the influence of multicollinearity of model variables. The sensitive areas of soil TN content in the SCI do not undergo significant changes due to different fertilization periods. Among them, the ratio spectral indices (RSIs) are in the range of 800–900 nm, 1900–1950 nm, and 2200–2300 nm, while the sensitive areas of the difference spectral index (DI) and Normalized difference spectral index (NDSI) are in the range of 1900–1950 nm and 2200–2300 nm. The combination of SCI and characteristic bands significantly improves the prediction accuracy of soil TN estimation models. The independent and comprehensive estimation models for each fertilization period based on the BP (back propagation) neural network optimized by the Mind Evolution Algorithm (MEA-BPNN) can achieve a more stable and accurate estimation of soil TN. Finally, using soil spectral characteristic bands selected through continuum removal (CR) transformation and SMLR, combined with SCI, the model based on the MEA-BPNN (CR-SCI-MEA-BPNN) has the best prediction performance. The modeling determination coefficients R2 for each fertilization period reached 0.94, 0.95, 0.92, and 0.94, respectively, with RMSE of 0.0032, 0.0024, 0.0035, and 0.0027. The R2 and RMSE of the modeling and validation set of the entire fertilization period comprehensive model are 0.899, 0.0038, and 0.89, 0.0041, respectively. The results of this article provide technical support for promoting the timely monitoring of soil TN content and guiding rational fertilization in apple orchards.

Exploring the biomedical potential of chitosan‐ceria nanocomposites: synthesis and characterizations

The objective of this study was to synthesize and evaluate the biological effectiveness of cerium oxide (CeO2) against various bacterial and fungal strains. The chitosan‐CeO2 nanocomposite was comprehensively characterized. The Fourier transform infrared (FTIR) spectra displayed a combination of bands that provided evidence for the existence of a composite complex between the chitosan (CS) structure and the Ce–O bands originating from CeO2 nanoparticles. SEM measurements showed uniform dispersion across the whole CS surface, and the morphological changes were clearly observed as the CeO2 nanoparticle content was increased. In contrast, CS‐CeO2 demonstrates enhanced antibacterial efficacy against both Gram‐positive and Gram‐negative pathogens. The MTT method was utilized to assess the cytotoxicity of the examined CS‐CeO2, with the aim of evaluating the cell viability of various cancer cell lines under varying ultraviolet (UV) exposures. The enhanced penetration of CS and CeO2 nanocomposites into cancer cells during their anticancer activity, even in the absence of UV light, led to an increased rate of cell death. The administration of greater dosages of CS and its CeO2 nanocomposites led to an increased generation of reactive oxygen species (ROS), which was observed to be associated with an enhancement in the efficacy of anticancer activity. The impact was additionally amplified through exposure to UV radiation. The nanocomposite thin films demonstrated much higher antioxidant activity against the DPPH radical as compared to ordinary vitamin C. The aforementioned observation was derived from an evaluation of the antioxidant properties of the subject utilizing the DPPH free radical scavenging technique.

Using Improved YOLOv5 and SegFormer to Extract Tailings Ponds from Multi-Source Data

This paper proposes a framework that combines the improved "You Only Look Once" version 5 (YOLOv5) and SegFormer to extract tailings ponds from multi-source data. Points of interest (POIs) are crawled to capture potential tailings pond regions. Jeffries–Matusita distance is used to evaluate the optimal band combination. The improved YOLOv5 replaces the backbone with the PoolFormer to form a PoolFormer backbone. The neck introduces the CARAFE operator to form a CARAFE feature pyramid network neck (CRF-FPN). The head is substituted with an efficiency decoupled head. POIs and classification data optimize improved YOLOv5 results. After that, the SegFormer is used to delineate the boundaries of tailings ponds. Experimental results demonstrate that the mean average precision of the improved YOLOv5s has increased by 2.78% compared to the YOLOv5s, achieving 91.18%. The SegFormer achieves an intersection over union of 88.76% and an accuracy of 94.28%.

Spectral-Spatial-Sensorial Attention Network with Controllable Factors for Hyperspectral Image Classification

Hyperspectral image (HSI) classification aims to recognize categories of objects based on spectral–spatial features and has been used in a wide range of real-world application areas. Attention mechanisms are widely used in HSI classification for their ability to focus on important information in images automatically. However, due to the approximate spectral–spatial features in HSI, mainstream attention mechanisms are difficult to accurately distinguish the small difference, which limits the classification accuracy. To overcome this problem, a spectral–spatial-sensorial attention network (S3AN) with controllable factors is proposed to efficiently recognize different objects. Specifically, two controllable factors, dynamic exponential pooling (DE-Pooling) and adaptive convolution (Adapt-Conv), are designed to enlarge the difference in approximate features and enhance the attention weight interaction. Then, attention mechanisms with controllable factors are utilized to build the redundancy reduction module (RRM), feature learning module (FLM), and label prediction module (LPM) to process HSI spectral–spatial features. The RRM utilizes the spectral attention mechanism to select representative band combinations, and the FLM introduces the spatial attention mechanism to highlight important objects. Furthermore, the sensorial attention mechanism extracts location and category information in a pseudo label to guide the LPM for label prediction and avoid details from being ignored. Experimental results on three public HSI datasets show that the proposed method is able to accurately recognize different objects with an overall accuracy (OA) of 98.69%, 98.89%, and 97.56%, respectively.

Near-Infrared Spectroscopic Study of Biotite–Phlogopite (Mg# = 30~99): OH-Stretching Modes and Mg# Content Prediction Equation

Biotite–phlogopite minerals are a complete Mg–Fe isomorphism series of phyllosilicates. A Fourier transform infrared spectroscopy (FTIR) and electron microprobe analysis (EMPA) were conducted on end-member phlogopite, Mg–biotite, and annite samples. In the mid-infrared region, absorption peaks were observed at 460, 1000, 3680, and 3710 cm−1 in the biotite group. Samples with higher Mg content exhibited stronger peaks assigned to OH vibrations and a weak absorption peak at 810 cm−1. In the near-infrared region, combination peaks were observed near 4200, 4300, and 4450 cm−1, with wavenumbers showing a linear inverse relationship with the Mg# [=100 × Mg/(Mg + FeT)] value. For annite, combination peaks occurred at 4173, 4292, and 4439 cm−1, decreasing by 10–15 cm−1 compared to end-member phlogopite. Judging the fundamental peaks of the combination band contributes to identifying suitable near-infrared characteristic peaks for quantitative research. The 4300 cm−1 absorption peak in biotite–phlogopite was assigned to OH-bending and -stretching vibrations, making it suitable for mineral identification and Mg# estimations across all biotite groups. The 4450 cm−1 characteristic peak, assigned to Al–O-stretching vibrations and OH-stretching vibrations, is suitable for accurately predicting Mg# values in high AlVI samples. The first overtones of biotite–phlogopite appeared at 7250 cm−1, with an average factor of 1.955 between the fundamental and corresponding overtones. This study aims to refine the patterns of OH-stretching vibrations and characteristic peak shifts in the near-infrared spectral region of phyllosilicate minerals, providing data references for planetary spectroscopy and ore deposit studies.

Evaluation and Selection of Multi-Spectral Indices to Classify Vegetation Using Multivariate Functional Principal Component Analysis

The identification, classification and mapping of different plant communities and habitats is of fundamental importance for defining biodiversity monitoring and conservation strategies. Today, the availability of high temporal, spatial and spectral data from remote sensing platforms provides dense time series over different spectral bands. In the case of supervised mapping, time series based on classical vegetation indices (e.g., NDVI, GNDVI, …) are usually input characteristics, but the selection of the best index or set of indices (which guarantees the best performance) is still based on human experience and is also influenced by the study area. In this work, several different time series, based on Sentinel-2 images, were created exploring new combinations of bands that extend the classic basic formulas as the normalized difference index. Multivariate Functional Principal Component Analysis (MFPCA) was used to contemporarily decompose the multiple time series. The principal multivariate seasonal spectral variations identified (MFPCA scores) were classified by using a Random Forest (RF) model. The MFPCA and RF classifications were nested into a forward selection strategy to identify the proper and minimum set of indices’ (dense) time series that produced the most accurate supervised classification of plant communities and habitat. The results we obtained can be summarized as follows: (i) the selection of the best set of time series is specific to the study area and the habitats involved; (ii) well-known and widely used indices such as the NDVI are not selected as the indices with the best performance; instead, time series based on original indices (in terms of formula or combination of bands) or underused indices (such as those derivable with the visible bands) are selected; (iii) MFPCA efficiently reduces the dimensionality of the data (multiple dense time series) providing ecologically interpretable results representing an important tool for habitat modelling outperforming conventional approaches that consider only discrete time series.

CN stretches around 4.4 microns dominate the IR absorption spectra of cyano-polycyclic aromatic hydrocarbons

ABSTRACT Anharmonic quantum chemical computations reveal a strong, narrow (width = 0.075 $\mu$m) band in the 4.3–4.5 $\mu$m region of the absorption spectra of the cyano-substituted polycyclic aromatic hydrocarbons (CN-PAHs) cyanonaphthalene, cyanoanthracene, cyanophenanthrene, and cyanopyrene. This narrow window with intense IR lines implies that CN-PAHs of various shapes and sizes offer little variation in both wavelength and intensity in this region. Subsequently, this band can be used as a tracer for CN-PAHs. The distinct features making up the band are assigned to mixed vibrational states consisting of the CN stretch fundamental and various combination bands, including in-plane CH bends, CC skeletal bends, and CC skeletal breathing motions. The extraordinarily large intrinsic intensity of the fundamental CN stretch is redistributed to nearby states via anharmonic coupling, which is readily captured when using second order vibrational perturbation theory with resonance polyad matrices. This redistribution of intensity leads to a complex spectrum. The intense bands in this wavelength region may contribute to the baseline continuum and undulating macroscopic structure seen in recent JWST NIRSpec observations.

Novel fusion strategy for image fusion using rescue hunt optimization-based modified guidance model

ABSTRACT A new method for image fusion introduces an inventive strategy for amalgamating data from multiple images, resulting in the creation of a single, improved output image. This approach aims to address the limitations and challenges associated with conventional fusion techniques, paving the way for improved results in various applications. In this research, a novel approach for image fusion is presented, featuring a rescue hunt optimisation-based modified guidance model (RHO-based MG model). The methodology leverages the non-subsampled contourlet transform (NSCT) and non-subsampled shear let transform (NSST) to construct the fusion transform using two input images, typically infrared and visual images. By hybridising high-frequency (HF) and low-frequency (LF) bands from both types of images, the fusion model generates the final HF and LF bands. A distinctive modified guidance strategy is employed in the development of these bands. The proposed approach utilises a rescue hunt algorithm developed through the combination of search and rescue optimisation (SARO) and grey wolf optimisation (GWO) behaviours. In image fusion, optimisation fine-tunes VGG-19 and RESNET 18 models to improve their ability to combine multiple images effectively. This process involves adjusting the models’ internal parameters using optimisation techniques. By analysing the features in different input images, these models learn to extract meaningful information and create a fused image that retains the important details from each source. This strategy is further enhanced by integrating the VGG-19 and RESNET 18 models. The fused image is composed of combined HF and LF bands, with the final result obtained through an inverse hybrid transform. Experimental results, conducted on a dataset of 25 images, demonstrate the effectiveness of the approach with metrics average gradient (AG), edge intensity (EI), PSNR, RMSE, SSIM, and variance attained the values of 24.71, 236.67, 54.96 dB, 0.22, 63.16, and 0.11, respectively. This innovative method offers a promising direction for enhancing image fusion quality and is highlighted by its unique integration of optimisation and guidance strategies.

Spectra of the D2O dimer in the O-D fundamental stretch region: The acceptor symmetric stretch fundamental and new combination bands.

The O-D stretch fundamental region of the deuterated water dimer, (D2O)2, is further studied using a pulsed supersonic slit jet and a tunable optical parametric oscillator infrared source. The previously unobserved acceptor symmetric O-D stretch fundamental vibration is detected, with Ka = 0 ← 0 and 1 ← 0 sub-bands at about 2669 and 2674cm-1, respectively. The analysis indicates that the various water dimer tunneling splittings generally decrease in the excited vibrational state, similar to the three other previously observed O-D stretch fundamentals. Two new (D2O)2 combination bands are observed, giving information on intermolecular vibrations in the excited O-D stretch states. The likely vibrational assignments for these and a previously observed combination band are discussed.

The infrared absorption spectrum of phenylacetylene and its deuterated isotopologue in the mid- to far-IR.

Anharmonicity strongly influences the absorption and emission spectra of polycyclic aromatic hydrocarbon (PAH) molecules. Here, IR-UV ion-dip spectroscopy experiments together with detailed anharmonic computations reveal the presence of fundamental, overtone, as well as 2- and 3-quanta combination band transitions in the far- and mid-infrared absorption spectra of phenylacetylene and its singly deuterated isotopologue. Strong absorption features in the 400-900 cm-1 range originate from CH(D) in-plane and out-of-plane wags and bends, as well as bending motions including the C≡C and CH bonds of the acetylene substituent and the aromatic ring. For phenylacetylene, every absorption feature is assigned either directly or indirectly to a single or multiple vibrational mode(s). The measured spectrum is dense, broad, and structureless in many regions but well characterized by computations. Upon deuteration, large isotopic shifts are observed. At frequencies above 1500 cm-1 for d1-phenylacetylene, a one-to-one match is seen when comparing computations and experiments with all features assigned to combination bands and overtones. The C≡C stretch observed in phenylacetylene is not observed in d1-phenylacetylene due to a computed 40-fold drop in intensity. Overall, a careful treatment of anharmonicity that includes 2- and 3-quanta modes is found to be crucial to understand the rich details of the infrared spectrum of phenylacetylene. Based on these results, it can be expected that such an all-inclusive anharmonic treatment will also be key for unraveling the infrared spectra of PAHs in general.

Rapid generation of massive thermodynamic datasets using frequency comb spectroscopy.

We demonstrate massively parallel spectroscopic measurements of 12C2H2 using an optical frequency comb. This allows for the rapid and simultaneous estimation of self-broadening and self-shifting of more than 50 optical transitions between 1512 and 1538nm. The use of a temperature-controlled sealed gas cell allows us to measure both pressure- and temperature-mediated broadening and shifting. We present the results for the pressure-mediated self-broadening and self-shifting coefficients for 59 optical lines that make up the v1 + v3 combination band and a selection of hot bands. Our ability to measure the broadening of numerous transitions allows for the confirmation of prior work that shows that there is no measurable vibrational dependence across all acetylene bands, despite the strong dependence of the broadening coefficient on the rotational number. We also present an extensive measurement of the temperature dependence of the self-broadening for each of these 59 lines. This work shows the revolutionary power afforded by the frequency combs for rapid generation of large datasets related to thermodynamic variations of the key spectroscopic parameters of important gases.

Fusion of different multispectral band combinations of Sentinel-2A with UAV imagery for crop classification

Fusion of different multispectral band combinations of Sentinel-2A with UAV imagery for crop classification

SPATIAL INVENTORY OF SOLAR PHOTOVOLTAIC (PV) INSTALLATIONS USING REMOTE SENSING AND MACHINE LEARNING: CASE OF PAMPANGA PROVINCE, PHILIPPINES

Abstract. In recent years, the cost of photovoltaic (PV) technologies significantly declined, boosting the expansion of solar PV installations in the country. This rapid development in solar PV utilization necessitates an effective detection method capable of delineating both utility-scale and distributed PV installations to generate a complete inventory of solar PV installations for status monitoring and implementation of appropriate programs of stakeholders and decision-makers. This study aims to detect and delineate solar PV installations in Pampanga, Philippines using different band combinations of Sentinel-2, Sentinel-1, and indices (NDVI, NDWI, and PVSI) through machine learning with the aid of open-source geographic information system and remote sensing software. Moreover, an alternative approach to identifying solar PVs using the combination of pixel-based classification (PBC) and object-based classification (OBC) was introduced. Training and validation data were acquired from the satellite images. The accuracy of each approach in PV detection was then compared using three classifiers: Support Vector Machine (SVM), Random Forest, and Naive Bayes. Results showed that SVM has the best performance for PBC while Random Forest demonstrated the highest accuracy for OBC. A post-processing procedure was also implemented using a set of spectral rules to further refine the results of image classification. The delineation accuracies of the post-processed data over the ground-truth data showed that the methodology is effective in delineating utility-scale installations for both Sentinel-2 and Planetscope. However, the detection of distributed PV systems showed limitations particularly when dealing with small solar PV installations (less than 45 pixels) due to Sentinel-2’s coarse spatial resolution.

Enhancing phenotyping efficiency in faba bean breeding: integrating UAV imaging and machine learning

Unmanned aerial vehicles (UAVs) equipped with high-resolution imaging sensors have shown great potential for plant phenotyping in agricultural research. This study aimed to explore the potential of UAV-derived red–green–blue (RGB) and multispectral imaging data for estimating classical phenotyping measures such as plant height and predicting yield and chlorophyll content (indicated by SPAD values) in a field trial of 38 faba bean (Vicia faba L.) cultivars grown at four replicates in south-eastern Norway. To predict yield and SPAD values, Support Vector Regression (SVR) and Random Forest (RF) models were utilized. Two feature selection methods, namely the Pearson correlation coefficient (PCC) and sequential forward feature selection (SFS), were applied to identify the most relevant features for prediction. The models incorporated various combinations of multispectral bands, indices, and UAV-based plant height values at four different faba bean development stages. The correlation between manual and UAV-based plant height measurements revealed a strong agreement with a correlation coefficient (R2) of 0.97. The best prediction of SPAD value was achieved at BBCH 50 (flower bud present) with an R2 of 0.38 and RMSE of 1.14. For yield prediction, BBCH 60 (first flower open) was identified as the optimal stage, using spectral indices yielding an R2 of 0.83 and RMSE of 0.53 tons/ha. This development stage presents an opportunity to implement targeted management practices to enhance yield. The integration of UAVs equipped with RGB and multispectral cameras, along with machine learning algorithms, proved to be an accurate approach for estimating agronomically important traits in faba bean. This methodology offers a practical solution for rapid and efficient high-throughput phenotyping in faba bean breeding programs.

Automatic Flood Detection from Sentinel-1 Data Using a Nested UNet Model and a NASA Benchmark Dataset

During flood events near real-time, synthetic aperture radar (SAR) satellite imagery has proven to be an efficient management tool for disaster management authorities. However, one of the challenges is accurate classification and segmentation of flooded water. A common method of SAR-based flood mapping is binary segmentation by thresholding, but this method is limited due to the effects of backscatter, geographical area, and surface characterstics. Recent advancements in deep learning algorithms for image segmentation have demonstrated excellent potential for improving flood detection. In this paper, we present a deep learning approach with a nested UNet architecture based on a backbone of EfficientNet-B7 by leveraging a publicly available Sentinel‑1 dataset provided jointly by NASA and the IEEE GRSS Committee. The performance of the nested UNet model was compared with several other UNet-based convolutional neural network architectures. The models were trained on flood events from Nebraska and North Alabama in the USA, Bangladesh, and Florence, Italy. Finally, the generalization capacity of the trained nested UNet model was compared to the other architectures by testing on Sentinel‑1 data from flood events of varied geographical regions such as Spain, India, and Vietnam. The impact of using different polarization band combinations of input data on the segmentation capabilities of the nested UNet and other models is also evaluated using Shapley scores. The results of these experiments show that the UNet model architectures perform comparably to the UNet++ with EfficientNet-B7 backbone for both the NASA dataset as well as the other test cases. Therefore, it can be inferred that these models can be trained on certain flood events provided in the dataset and used for flood detection in other geographical areas, thus proving the transferability of these models. However, the effect of polarization still varies across different test cases from around the world in terms of performance; the model trained with the combinations of individual bands, VV and VH, and polarization ratios gives the best results.