Unsupervised classification of remote sensing imagery using multi-sensor data fusion

Encoding of multispectral and hyperspectral image data using wavelet transform and gain shape vector quantization

Suaeda salsa (S. salsa) has a significant protective effect on salt marshes in coastal wetlands. In this study, the abilities of airborne multispectral images, spaceborne hyperspectral images, and LiDAR data in spatial distribution extraction and aboveground biomass (AB) estimation of S. salsa were explored for mapping the spatial distribution of S. salsa AB. Results showed that the increasing spectral and structural features were conducive to improving the classification accuracy of wetland vegetation and the AB estimation accuracy of S. salsa. The fusion of hyperspectral and LiDAR data provided the highest accuracies for wetlands classification and AB estimation of S. salsa in the study. Multispectral images alone provided relatively high user's and producer's accuracies of S. salsa classification (87.04% and 88.28%, respectively). Compared to multispectral images, hyperspectral data with more spectral features slightly improved the Kappa coefficient and overall accuracy. The AB estimation reached a relatively reliable accuracy based only on hyperspectral data (R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> of 0.812, root-mean-square error of 0.295, estimation error of 24.56%, residual predictive deviation of 2.033, and the sums of squares ratio of 1.049). The addition of LiDAR data produced a limited improvement in the process of extraction and AB estimation of S. salsa. The spatial distribution of mapped S. salsa AB was consistent with the field survey results. This study provided an important reference for the effective information extraction and AB estimation of wetland vegetation S. salsa.

PurposeThe K-means (KM) clustering algorithm is extremely responsive to the selection of initial centroids since the initial centroid of clusters determines computational effectiveness, efficiency and local optima issues. Numerous initialization strategies are to overcome these problems through the random and deterministic selection of initial centroids. The random initialization strategy suffers from local optimization issues with the worst clustering performance, while the deterministic initialization strategy achieves high computational cost. Big data clustering aims to reduce computation costs and improve cluster efficiency. The objective of this study is to achieve a better initial centroid for big data clustering on business management data without using random and deterministic initialization that avoids local optima and improves clustering efficiency with effectiveness in terms of cluster quality, computation cost, data comparisons and iterations on a single machine.Design/methodology/approachThis study presents the Normal Distribution Probability Density (NDPD) algorithm for big data clustering on a single machine to solve business management-related clustering issues. The NDPDKM algorithm resolves the KM clustering problem by probability density of each data point. The NDPDKM algorithm first identifies the most probable density data points by using the mean and standard deviation of the datasets through normal probability density. Thereafter, the NDPDKM determines K initial centroid by using sorting and linear systematic sampling heuristics.FindingsThe performance of the proposed algorithm is compared with KM, KM++, Var-Part, Murat-KM, Mean-KM and Sort-KM algorithms through Davies Bouldin score, Silhouette coefficient, SD Validity, S_Dbw Validity, Number of Iterations and CPU time validation indices on eight real business datasets. The experimental evaluation demonstrates that the NDPDKM algorithm reduces iterations, local optima, computing costs, and improves cluster performance, effectiveness, efficiency with stable convergence as compared to other algorithms. The NDPDKM algorithm minimizes the average computing time up to 34.83%, 90.28%, 71.83%, 92.67%, 69.53% and 76.03%, and reduces the average iterations up to 40.32%, 44.06%, 32.02%, 62.78%, 19.07% and 36.74% with reference to KM, KM++, Var-Part, Murat-KM, Mean-KM and Sort-KM algorithms.Originality/valueThe KM algorithm is the most widely used partitional clustering approach in data mining techniques that extract hidden knowledge, patterns and trends for decision-making strategies in business data. Business analytics is one of the applications of big data clustering where KM clustering is useful for the various subcategories of business analytics such as customer segmentation analysis, employee salary and performance analysis, document searching, delivery optimization, discount and offer analysis, chaplain management, manufacturing analysis, productivity analysis, specialized employee and investor searching and other decision-making strategies in business.

Rain is one of the hydrological cycles which is a cycle of water rotation from the earth to the atmosphere and back to the earth continuously. High Rainfall may cause some areas that are in lowlands or those with low water infiltration systems will be very susceptible to flooding. For that it is necessary to have a system to classify weather data and rainfall in each city and district so the city that has high rainfall and extreme weather can be given special attention to prevent any natural disaster like flooding. The collected data will be processed with K-Means algorithm to classify the cities or district that have low, medium, high, or very high rainfall data. In the K-Means algorithm the amount of k or cluster usually determined by randomly, on this project will be used a method that is Elbow Method to determine the value of k or cluster and Silhouette Coefficient Method will be used for testing the quality amount of a cluster. The data that will be used is the rainfall data from dataonline.bmkg.go.id at a certain period of time to be classified using the K-Means algorithm. The elbow method and the silhouette method can be used in selecting a good optimal number of clusters, and both methods mostly have the same results in determining the optimal number of clusters, it can be seen that the calculation of accuracy between using the optimal number of clusters is higher rather than not using the amount optimal number of clusters. This can be seen in the results of the clustering in Semarang on February 1 - 28, 2021, when using the amount of K = 4 produce the accuracy result 92.8571429 %, while when using the optimal number of cluster K=3 the accuracy result is higher (97.6190476 %). In the Cilacap city classification on April 1-30 2021, the elbow method and the silhouette coefficient method produce different optimal cluster results, but the accuracy obtained when using the optimal number of clusters from the silhouette coefficient (85.7142857 %) is higher than using the optimal cluster from the elbow method.(74.6031746 %), but when the data is processed with centroid on table 5.10, the elbow method and silhouette coefficient method produce the same amount of optimal number of clusters is 2. This shows that differences in the use of the initial centroid point can affect the results of the elbow method and the silhouette coefficient method

Infection by the fungus Verticillium dahliae (Vd) and the bacterium Xylella fastidiosa (Xf) threatens the production of olives (Olea europaea L.) and almonds (Prunus dulcis Mill.) worldwide. Producing symptoms that resemble water stress or nutrient deficiency, infection by these vascular pathogens restricts water and nutrient flow through the xylem. Hyperspectral, narrow-band multispectral, and thermal imagery acquired at a high spatial resolution can detect disease symptoms, even before they are visible, potentially allowing growers to distinguish infected plants from those affected by confounding environmental stresses. Nevertheless, operational detection of vascular disease using high-resolution commercial satellite multispectral images remains to be evaluated. Here, we assessed the capacity of high-resolution Worldview-2 and -3 multispectral imagery to detect Xf and Vd infections in olive and almond orchards in Spain, Italy, and Australia between 2011 and 2021. We compared the accuracy of detecting both pathogens using the satellite imagery with results obtained using aerial high-resolution hyperspectral and thermal imaging, with model-inverted plant traits, solar-induced chlorophyll fluorescence (SIF), and thermal data as a reference. Our results using spectral plant traits to examine disease progression at all stages showed that traits and their importance varied as a function of disease severity. Worldview-2 and -3 detected the disease incidence with overall accuracies ranging from 0.63 to 0.83 and kappa coefficients (κ) ranging from 0.29 to 0.68. Nevertheless, detecting the early stages of disease with multispectral satellite data yielded poorer results, with κ values of 0.22–0.45, compared with κ values of 0.3–0.69 obtained from hyperspectral data. Typical multispectral bandsets available from satellite sensors cannot measure important plant traits such as the blue index NPQI, xanthophyll proxy PRIn, SIF, and anthocyanin levels, thus explaining the poorer results obtained from multispectral satellite data for the early detection of vascular diseases. Adding a thermal-based crop water stress indicator to the satellite data improved the overall accuracies by 10–15% and increased κ by >0.2 units. This work shows that commercial multispectral high-spatial resolution imagery can be used to detect intermediate and advanced Xf and Vd infection, but that the early detection of disease symptoms requires hyperspectral and thermal data.

Improving estimation of maize leaf area index by combining of UAV-based multispectral and thermal infrared data: The potential of new texture index

Urban reservoirs are important for drinking water services and urban living. However, potentially toxic cyanobacteria blooms are frequently present due to human pollution and might threaten the urban water supply. Conveniently, cyanobacteria can be monitored by remote sensing-based approaches based on the spectral features of C-Phycocyanin (PC). Furthermore, methods leveraging Machine Learning Algorithms (MLA) for PC estimation from hyperspectral data have highlighted the potential to estimate PC more accurately - even at low concentrations. Since relatively few methodologies for PC retrieval in tropical environments have been developed or validated, this research evaluated PRISMA hyperspectral data processed with three MLA (Random Forest, Extreme Gradient Boost, and Support Vector Machines) to estimate PC concentrations in the Billings reservoir, Brazil. The same MLA were used to generate PC models using Wordview-3 and Landsat-8/OLI simulated data to assess the potential gain of using hyperspectral over multispectral data. A PRISMA image was processed with three atmospheric correction methods and validated with co-located in-situ data, where the best atmospherically corrected product was used to generate synthetic Landsat-8/OLI and Worldview-3 images. The PC models were calibrated and validated through Monte Carlo simulation using field radiometric and biological data (Chlorophyll-a, PC, and phytoplankton taxonomy) collected in eight field campaigns (N = 115). The PRISMA and the synthetic multispectral images were used for a second round of models’ validation using co-located PC measurements (match-up window ± 4 h). The global PC Mixture Density Network was also applied to the PRISMA data, and the estimates were compared with the other MLA. The results showed that the standard PRISMA surface reflectance product provided the best atmospheric correction (MAE < 20% for the 500–700 nm bands), while ACOLITE and 6SV underperformed it from two to more than ten-fold. Cyanobacteria species were abundant in 96% of the taxonomical samples, even though relatively low PC concentrations were found (PC from 0 to 301.81 μg/L and median PC = 2.9 μg/L). The global Mixture Density Network sharply overestimated PC (MAE = 280% and Bias = 280%), potentially due to Billings reservoir’s low PC:Chlorophyll-a ratio relative to the original training dataset. PRISMA/Random Forest (MAE = 45%) achieved the lowest error for orbital PC estimate, while Extreme Gradient Boost outperformed the other MLA using Worldview-3 (MAE = 49%) and Landsat-8 (MAE = 74%) synthetic imagery. Therefore, the results suggest hyperspectral and multispectral orbital data aligned with MLA are feasible for monitoring PC, even for waters containing low PC concentrations and reduced PC:Chlorophyll-a ratios.

Research on LWIR multispectral imaging detection technology carried out in the key national defense laboratory in Tianjin University is introduced in this paper. Firstly, a kind of infrared multispectral image simulation method based on multispectral or hyperspectral images data in the VIS/NIR band is recommended. The combined strategy of unsupervised and supervised classification methods is put forward to efficiently realize auto-matching and labeling of pixels. Then, using the infrared image simulation technology, infrared multispectral simulation images can be generated highly similar to real natural environments, which are valuable to the development of LWIR multispectral spectrometers, as well as research on multispectral detection algorithms. Secondly, the co-image plane imaging detection technique is presented as well as the attempt to make the small LWIR multispectral imaging detector based on such concept. A fourband prototype has been achieved in VIS/NIR band, verifying the feasibility and validity of this technique.

Hyperspectral (HS) images obtained from space are useful for monitoring different natural phenomena on regional to global scales. The Environmental Mapping and Analysis Program (EnMAP) is a satellite recently launched by Germany to monitor the environment and explore the capabilities of hyperspectral sensors in the 420 and 2450 nm range of the spectrum. However, the data captured by the EnMAP mission have a ground sampling distance (GSD) of 30 m. This limits the use of the data for some applications that require higher spatial resolution (&lt;10 m). This study examines the potential for improving the resolution of hyperspectral data using high resolution multispectral (MS) data obtained by Cubesats. Specifically, this work uses the data captured by the PlanetScope constellation, which has more than 150 CubeSats in low Earth orbit, with a high spatial and temporal resolution. The approach adopted leverages (1) the spectral capability of the hyperspectral EnMAP sensor, with a bandwidth of 6.5 nm in the visible and near infrared (VNIR) range (420&amp;#8211;1000 nm) and 10 nm in the SWIR range (900&amp;#8211;2450 nm), and (2) the spatial capability of the multispectral PlanetScope data, with a GSD of 3 meters, to enable significant spatial improvements due to its high spatial resolution. The main components of this work include: (i) area of interest clipping (ii) data co-registration, (iii) HS-MS data fusion, and (iv) quality assessments using the Jointly Spectral and Spatial Quality Index (QNR). In this study, a 2 km x 2 km area of interest was selected in the Malaucene region of France, where six state-of-the-art HS-MS fusion methods were evaluated: (1) fast multi-band image fusion algorithm (FUSE), (2) coupled nonnegative matrix factorization (CNMF), (3) smoothing filtered-based intensity modulation (SFIMHS), (4) maximum a posteriori stochastic mixing model (MAPSMM), (5) Hyperspectral Superresolution (HySure), and (6) generalized laplacian pyramid hypersharpening (GLPHS). Quality assessments of the enhanced data showed that high spectral and spatial fidelity are maintained, with the best performing fusion method being FUSE with a QNR of 0.625 followed by the MAPSMM method with a QNR of 0.604. Overall, this study advocates the benefits associated with the fusion of hyperspectral and multispectral data to obtain enhanced EnMAP data at 3 m GSD.&amp;#160;

ZY-1 02D is China’s first civil hyperspectral (HS) operational satellite, developed independently and successfully launched in 2019. It can collect HS data with a spatial resolution of 30 m, 166 spectral bands, a spectral range of 400~2500 nm, and a swath width of 60 km. Its competitive advantages over other on-orbit or planned satellites are its high spectral resolution and large swath width. Unfortunately, the relatively low spatial resolution may limit its applications. As a result, fusing ZY-1 02D HS data with high-spatial-resolution multispectral (MS) data is required to improve spatial resolution while maintaining spectral fidelity. This paper conducted a comprehensive evaluation study on the fusion of ZY-1 02D HS data with ZY-1 02D MS data (10-m spatial resolution), based on visual interpretation and quantitative metrics. Datasets from Hebei, China, were used in this experiment, and the performances of six common data fusion methods, namely Gram-Schmidt (GS), High Pass Filter (HPF), Nearest-Neighbor Diffusion (NND), Modified Intensity-Hue-Saturation (IHS), Wavelet Transform (Wavelet), and Color Normalized Sharping (Brovey), were compared. The experimental results show that: (1) HPF and GS methods are better suited for the fusion of ZY-1 02D HS Data and MS Data, (2) IHS and Brovey methods can well improve the spatial resolution of ZY-1 02D HS data but introduce spectral distortion, and (3) Wavelet and NND results have high spectral fidelity but poor spatial detail representation. The findings of this study could serve as a good reference for the practical application of ZY-1 02D HS data fusion.

In recent years, using multispectral remote sensing data to change detection has been a hot issue. However, the limited number of spectral segments cannot accurately classify ground objects, which will affect the performance of change detection. To overcome this problem, in this paper, we propose a multispectral image change detection method based on a hyperspectral reconstruction network. The original multispectral data is used to generate hyperspectral data with richer spectral information, and then the generated data is used for change detection. The whole network consists of a reconstruction network and a change detection network. Based on the input multispectral data, a small amount of hyperspectral data is used to assist the training. In addition, we design a weighted loss to balance the two subnetworks in the training stage. In the test stage, the network can automatically recover hyperspectral data from multispectral data for change detection. The experimental results on two data sets show that the hyperspectral reconstruction method can improve the accuracy of multispectral images.

PurposeCombining the collected human body variables by a 3D body scanner and the research results of medical computed tomography (CT) imaging, this research aims to develop a military bulletproof vest that is both protective and fit. In particular, the protective part must be able to cover the vital human internal organs completely. The results of this research help to make military bulletproof vests of different sizes for Taiwanese male and female soldiers. At the same time, the research results can provide a reference for the industry of making special-purpose clothing.Design/methodology/approach17 important human body variables of 988 participants (male: 716, 72.5%; female 272, 27.5%) are used for the analysis. The K-means algorithm firstly builds clusters of different body shapes for both sexes; the silhouette coefficient helps to determine the optimal number of clusters to be six. Thus, the standard size of the bulletproof vest for soldiers is determined. The specifications of the bulletproof vest's inner core and textile vest are calculated for each cluster user. Our research then makes twelve prototypes of the bulletproof vest. After that, 12 subjects are invited to try on the new version (the vest designed in this study) and the old version (the vest currently used) to contrast the differences between the two.FindingsAccording to the index of the silhouette coefficient, the optimal number of clusters is determined to be six for both male and female clusters. Therefore, this study has designed six sizes of the bulletproof vest for male and female soldiers in Taiwan. After trying the new and old vests on, the subjects all indicate that the new vest fits better than the old one. In addition, the coverage of the bulletproof vest designed in this study is 94.38% for male users and 92.75% for female users.Originality/valueThe design of bulletproof vests must take note of the fit of the clothing itself and its protective function. Apart from the size design of general clothing only focusing on the human shape exteriorly, the bulletproof vest also needs to pay attention to the relative positions of vital organs inside the human body. Besides, for practical applications, it is quite effective to use the silhouette coefficient to determine the results of cluster analysis. Thus, the value of this research lies in the cross-field combination, enabling the integration of body measurement, data science and clothing design. Generally, bulletproof vests of newly designed sizes can meet the requirements of Taiwan's military. The research results can be used in the development of various military clothing for Taiwanese military personnel. At the same time, the results can be provided to the clothing industry as relevant parameters for designing unique functional clothing.

Studies were conducted in 2001 and 2002 to determine the effect of POST herbicides on the spectral reflectance of corn. POST corn herbicides evaluated included 2,4-D, atrazine, bromoxynil, dicamba + diflufenzopyr, nicosulfuron, and primisulfuron. Multispectral and hyperspectral data were collected and spectral properties were analyzed using SAS procedures and MultiSpec image analysis. Corn treated with POST applications of atrazine and primisulfuron could not be distinguished from nontreated corn regardless of data type or analysis method used. 2,4-D and dicamba + diflufenzopyr were the most readily distinguished from nontreated corn plots using both hyperspectral and multispectral data.

We classified 922 urban biotopes from 11 different biotope types in a 50.6 km <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> study area in Berlin, Germany. As input advanced data products were derived from hyperspectral and simulated multispectral data. Urban surface materials were derived from the hyperspectral data by classification and linear spectral unmixing. Multispectral data was classified using four different per-pixel and object-oriented classifiers. The results show that our developed method for biotope classification works well with hyperspectral and with multispectral input data yielding comparable overall accuracies of 88.1 and 91.3 percent.

Shallot plant diseases can reduce yields by up to 50% of total land area. Currently, shallot plant disease identification relies on direct observation, which is less effective and efficient due to varying intensities of disease and large cultivation areas. This study aims to develop a predictive model for shallot disease severity using multispectral drone imagery, apply Artificial Neural Network (ANN) algorithm to analyze multispectral band data, and evaluate the model's performance. The study used ANN algorithm with multi-layer perceptron regressor, involving following stages such as dataset acquisition, dataset stitching, dataset filtering and feature extraction, model development, and model evaluation. Multispectral data were taken using DJI Mavic 3 Multispectral drone, resulting 696 images per bands that were stitched into orthophoto map. The filtering process of plant objects yielded better model training results compared to unfiltered data. The optimal ANN model structure was identified as 4-6-2-1, with R² value of 0.9194 and MAE value of 0.0618. Model testing results demonstrated that using four input bands (G, R, RE, NIR) provided the best performance with R² value of 0.9194, followed by combination of two bands (R, RE) with R² value of 0.8883. This indicated that the R and RE bands were most strongly correlated with shallot disease severity. Keywords: Drone, Multi-layer perceptron, Multispectral imagery, Plant disease, Shallot.