Spectral Mixture Analysis Research Articles

Grain yield prediction using multi-temporal UAV-based multispectral vegetation indices and endmember abundance in rice

Timely and accurately predicting grain yield before harvest is of great importance for rice production management and grain trade. Numerous methods based on remote sensing (RS) technology have explored to estimate rice grain yield. However, in most cases, these methods are negatively affected by the mixed pixels of RS images due to the effect of background and panicles. To resolve such issues, the abundance information of leaves, soil and water background and rice panicles were extracted from the multispectral images of unmanned aerial vehicle (UAV) for the multiple endmember spectral mixture analysis (MESMA) method. Based on the analysis of contribution of vegetation index (VI) and abundance (ABD) to rice grain yield, a rice grain yield prediction model was developed by combining multi-stage time-series, ABD and VI. Results showed that MESMA can mitigate endmember variability in the estimation of rice yield, and achieve higher accuracy than conventional spectral mixture analysis (SMA). The NDRE and the sum of leaf and panicle abundance (ABDL+P) can be well correlated to grain yield before heading stage (R2 = 0.75) and at heading stage (R2 = 0.72), respectively. In comparison to them, the multi-stage time-series model consisted of VI and ABD [∑(VI&ABD)] produces the highest correlation (R2 = 0.80). It could also resolve the issues about the underestimation of yield using different datasets from various multi-spectral camera in comparison to the single-parameter models ∑VI and ∑ABD, and produce the good validation accuracy with R2 = 0.73, RRMSE= 0.22 and R2 = 0.75, RRMSE= 0.15, respectively. This study suggests that the combination of UAV multi-temporal VI and ABD data can achieve accurate prediction of rice grain yield. This method effectively utilizes the optical information of leaves and rice panicles and reduces background effects, which provides a new idea for accurate rice yield prediction.

Abundance considerations for modeling yield of rapeseed at the flowering stage.

To stabilize the edible oil market, it is necessary to determine the oil yield in advance, so the accurate and fast technology of estimating rapeseed yield is of great significance in agricultural production activities. Due to the long flowering time of rapeseed and the characteristics of petal color that are obviously different from other crops, the flowering period can be carefully considered in crop classification and yield estimation. A field experiment was conducted to obtain the unmanned aerial vehicle (UAV) multispectral images. Field measurements consisted of the reflectance of flowers, leaves, and soils at the flowering stage and rapeseed yield at physiological maturity. Moreover, GF-1 and Sentinel-2 satellite images were collected to compare the applicability of yield estimation methods. The abundance of different organs of rapeseed was extracted by the spectral mixture analysis (SMA) technology, which was multiplied by vegetation indices (VIs) respectively to estimate the yield. For the UAV-scale, the product of VIs and leaf abundance (AbdLF) was closely related to rapeseed yield, which was better than the VIs models for yield estimation, with the coefficient of determination (R2) above 0.78. The yield estimation models of the product of normalized difference yellowness index (NDYI), enhanced vegetation index (EVI) and AbdLF had the highest accuracy, with the coefficients of variation (CVs) below 10%. For the satellite scale, most of the estimation models of the product of VIs and rapeseed AbdLF were also improved compared with the VIs models. The yield estimation models of the product of AbdLF and renormalized difference VI (RDVI) and EVI (RDVI×AbdLF and EVI×AbdLF) had the steady improvement, with CVs below 13.1%. Furthermore, the yield estimation models of the product of AbdLF and normalized difference VI (NDVI), visible atmospherically resistant index (VARI), RDVI, and EVI had consistent performance at both UAV and satellite scales. The results showed that considering SMA could improve the limitation of using only VIs to retrieve rapeseed yield at the flowering stage. Our results indicate that the abundance of rapeseed leaves can be a potential indicator of yield prediction during the flowering stage.

Assessing the Magnitude of the Amazonian Forest Blowdowns and Post-Disturbance Recovery Using Landsat-8 and Time Series of PlanetScope Satellite Constellation Data

Blowdown events are a major natural disturbance in the central Amazon Forest, but their impact and subsequent vegetation recovery have been poorly understood. This study aimed to track post-disturbance regeneration after blowdown events in the Amazon Forest. We analyzed 45 blowdown sites identified after September 2020 at Amazonas, Mato Grosso, and Colombia jurisdictions using Landsat-8 and PlanetScope NICFI satellite imagery. Non-photosynthetic vegetation (NPV), green vegetation (GV), and shade fractions were calculated for each image and sensor using spectral mixture analysis in Google Earth Engine. The results showed that PlanetScope NICFI data provided more regular and higher-spatial-resolution observations of blowdown areas than Landsat-8, allowing for more accurate characterization of post-disturbance vegetation recovery. Specifically, NICFI data indicated that just four months after the blowdown event, nearly half of ΔNPV, which represents the difference between the NPV after blowdown and the NPV before blowdown, had disappeared. ΔNPV and GV values recovered to pre-blowdown levels after approximately 15 months of regeneration. Our findings highlight that the precise timing of blowdown detection has huge implications on quantification of the magnitude of damage. Landsat data may miss important changes in signal due to the difficulty of obtaining regular monthly observations. These findings provide valuable insights into vegetation recovery dynamics following blowdown events.

First evaluation of fire severity retrieval from PRISMA hyperspectral data

The unprecedented availability of spaceborne hyperspectral data has great potential to provide fire severity estimates that align with post-fire management needs, overcoming complex logistics and data acquisition costs of airborne hyperspectral sensors, and the suboptimal sensitivity of broadband data to several post-fire ground components. We analyzed the feasibility of the PRISMA mission -one of the first spaceborne spectrometers operationally active- to assess fire severity by leveraging hyperspectral data dimensionality through the retrieval of sub-pixel components directly related to fire severity in the field. Multispectral data provided by Sentinel-2, commonly used in fire severity quantitative assessments, were used as a benchmark method. Multiple endmember spectral mixture analysis (MESMA) was used to retrieve fractional cover of char, photosynthetic vegetation (PV), as well as non-photosynthetic vegetation and soil (NPVS) from post-fire PRISMA Level 2D and Sentinel-2 Level 2A scenes in one of the largest wildfires ever recorded in the western Mediterranean Basin. Ground-truth data were obtained using the Composite Burn Index (CBI) to procure three field-measured severity metrics: vegetation, soil and site. The relationship between the CBI data on a continuum scale and the cover of char, PV and NPVS image fractions retrieved from PRISMA and Sentinel-2 was assessed through Random Forest regression (RFR). Likewise, Ordinal Forests (OF) algorithm was used to classify categorized CBI data (low, moderate and high fire severity). PRISMA-based RFR fire severity estimates at vegetation, soil and site levels (R2 = 0.64–0.79 and RMSE = 0.33–0.41) outperformed those of Sentinel-2 (R2 = 0.27–0.53 and RMSE = 0.54–0.60), and were in line with previous studies using airborne hyperspectral sensors at higher spatial resolution. Fire severity underestimation for high field CBI values was almost unnoticeable in the PRISMA estimates. Categorical fire severity, not currently estimated using hyperspectral data but with high interest in post-fire management, were accurately predicted by PRISMA-based OF classification, with consistent user's and producer's accuracy for each fire severity category. The high confusion between moderate and low/high fire severity categories, typical when unmixing broadband multispectral data, was overcome by the PRISMA-based classification scheme. Our results suggest that new spaceborne spectrometer missions can support reliable fire severity assessments equivalent to airborne spectrometers, but readily applicable to large-scale assessments of extreme wildfire events.

Toward automated infrared spectral analysis in community drug checking.

The body of knowledge surrounding infrared spectral analysis of drug mixtures continues to grow alongside the physical expansion of drug checking services. Technicians trained in the analysis of spectroscopic data are essential for reasons that go beyond the accuracy of the analytical results. Significant barriers faced by people who use drugs in engaging with drug checking services include the speed and accuracy of the results, and the availability and accessibility of the service. These barriers can be overcome by the automation of interpretations. A random forest model for the detection of two compounds, MDA and fluorofentanyl, was trained and optimized with drug samples acquired at a community drug checking site. This resulted in a 79% true positive and 100% true negative rate for MDA, and 61% true positive and 97% true negative rate for fluorofentanyl. The trained models were applied to selected drug samples to demonstrate a proposed workflow for interpreting and validating model predictions. The detection of MDA was demonstrated on three mixtures: (1) MDMA and MDA, (2) MDA and dimethylsulfone, and (3) fentanyl, etizolam, and benzocaine. The classification of fluorofentanyl was applied to a drug mixture containing fentanyl, fluorofentanyl, 4-anilino-N-phenethylpiperidine, caffeine, and mannitol. Feature importance was calculated using shapely additive explanations to better explain the model predictions and k-nearest neighbors was used for visual comparison to labelled training data. This is a step toward building appropriate trust in computer-assisted interpretations in order to promote their use in a harm reduction context.

Regression-based surface water fraction mapping using a synthetic spectral library for monitoring small water bodies

ABSTRACT Small water bodies (SWBs), such as ponds and on-farm reservoirs, are a key part of the hydrological system and play important roles in diverse domains from agriculture to conservation. The monitoring of SWBs has been greatly facilitated by medium-spatial-resolution satellite images, but the monitoring accuracy is considerably affected by the mixed-pixel problem. Although various spectral unmixing methods have been applied to map sub-pixel surface water fractions for large water bodies, such as lakes and reservoirs, it is challenging to map SWBs that are small in size relative to the image pixel and have dissimilar spectral properties. In this study, a novel regression-based surface water fraction mapping method (RSWFM) using a random forest and a synthetic spectral library is proposed for mapping 10 m spatial resolution surface water fractions from Sentinel-2 imagery. The RSWFM inputs a few endmembers of water, vegetation, impervious surfaces, and soil to simulate a spectral library, and considers spectral variations in endmembers for different SWBs. Additionally, RSWFM applies noise-based data augmentation on pure endmembers to overcome the limitation often arising from the use of a small set of pure spectra in training the regression model. RSWFM was assessed in ten study sites and compared with the fully constrained least squares (FCLS) linear spectral mixture analysis, multiple endmember spectral mixture analysis (MESMA), and the nonlinear random forest (RF) regression without data-augmentation. The results showed that RSWFM decreases the water fraction mapping errors by ~ 30%, ~15%, and ~ 11% in root mean square error compared with the linear FCLS, MESMA unmixings, and the nonlinear RF regression without data-augmentation respectively. RSWFM has an accuracy of approximately 0.85 in R2 in estimating the area of SWBs smaller than 1 ha.

RSARE: A physically-based vegetation index for estimating wheat green LAI to mitigate the impact of leaf chlorophyll content and residue-soil background

The green leaf area index (LAI) is an important structural parameter that can be used for monitoring plant transpiration and carbon cycling over large spatial extents. LAI is also critical for understanding biophysical processes and predicting crop productivity. However, the retrieval of wheat green LAI based on canopy reflectance is always affected by the background material. For example, in the Yangtze River Basin of China, rice residues are typically returned to rice–wheat rotation fields. Thus the background for observing wheat canopy varies from a mixture of traditional wheat-soil components to wheat-residue or wheat-residue-soil, posing a significant challenge for accurate LAI estimation at the early stages of crop growth. Furthermore, when current vegetation indices (VIs) are used to estimate LAI, leaf chlorophyll content (LCC) and field moisture are two additional confounding factors. To resolve these issues, we propose a novel residue-soil adjusted red edge difference index (RSARE), which draws on concepts from a simple physical algorithm, i.e., linear spectral mixture analysis (LSMA). The results of field, satellite and modeling experiments demonstrate that the RSARE-LAI model is generally not sensitive to LCC, or to variations in residue-soil and traditional soil backgrounds, and estimates LAI with high accuracy (RMSEval = 0.55, RRMSEval=20.71%). In comparison to traditional VI-LAI maps, RASRE-LAI maps are less sensitive to confounding factors associated with the background components, field moisture, LCC, and both inter-annual and geographical differences. This novel residue-soil background-resistant RSARE particularly improves the accuracy of wheat LAI estimation at low LAI levels, thus facilitating large-scale mapping of LAI in the early growing season.

Estimation and Validation of Sub-Pixel Needleleaf Cover Fraction in the Boreal Forest of Alaska to Aid Fire Management

Wildfires, which are a natural part of the boreal ecosystem in Alaska, have recently increased in frequency and size. Environmental conditions (high temperature, low precipitation, and frequent lightning events) are becoming favorable for severe fire events. Fire releases greenhouse gasses such as carbon dioxide into the environment, creating a positive feedback loop for warming. Needleleaf species are the dominant vegetation in boreal Alaska and are highly flammable. They burn much faster due to the presence of resin, and their low-lying canopy structure facilitates the spread of fire from the ground to the canopy. Knowing the needleleaf vegetation distribution is crucial for better forest and wildfire management practices. Our study focuses on needleleaf fraction mapping using a well-documented spectral unmixing approach: multiple endmember spectral mixture analysis (MESMA). We used an AVIRIS-NG image (5 m), upscaled it to 10 m and 30 m spatial resolutions, and applied MESMA to all three images to assess the impact of spatial resolution on sub-pixel needleleaf fraction estimates. We tested a novel method to validate the fraction maps using field data and a high-resolution classified hyperspectral image. Our validation method produced needleleaf cover fraction estimates with accuracies of 73%, 79%, and 78% for 5 m, 10 m, and 30 m image data, respectively. To determine whether these accuracies varied significantly across different spatial scales, we used the McNemar statistical test and found no significant differences between the accuracies. The findings of this study enhance the toolset available to fire managers to manage wildfire and for understanding changes in forest demography in the boreal region of Alaska across the high-to-moderate resolution scale.

Mapping Alpine Grassland Fraction Coverage Using Zhuhai-1 OHS Imagery in the Three River Headwaters Region, China

The widely spread alpine grassland ecosystem in the Three River Headwaters Region (TRHR) plays an essential ecological role in carbon sequestration and soil and water conservation. In this study, we test the latest high spatial resolution hyperspectral (Zhuhai-1 OHS) remote sensing imagery to examine different alpine grassland coverage levels using Multiple Endmember Spectral Mixture Analysis (MESMA). Our results suggest that the 3-endmember (3-EM) MESMA model can provide the highest image pixel unmixing percentage, with a percentage exceeding 97% and 96% for pixel scale and landscape scale, respectively. The overall accuracy shows that Zhuhai-1 OHS imagery obtained the highest overall accuracy (83.7%, k = 0.77) in the landscape scale, but in the pixel scale, it is not as good as Landsat 8 OLI imagery. Overall, we can conclude that the hyperspectral imagery combined 3-EM MESMA model performs better in both pixel scale and landscape scale alpine grassland coverage mapping, while the multispectral imagery with the 3-EM MESMA model can satisfy requirements of alpine grassland coverage mapping at the pixel scale. The approaches and workflow to mapping alpine grassland in this study can help monitor alpine grassland degradation; not only in the Qinghai–Tibetan Plateau (QTP), but also in other grassland ecosystems.

Effects of spectral variability due to sediment and bottom characteristics on remote sensing for suspended sediment in shallow rivers

Advances in remote sensing techniques for water environments have led to acquisition of abundant data on suspended sediment concentration (SSC). However, confounding factors, such as particle sizes, mineral properties, and bottom materials, have not been fully studied, despite their substantial interference with the detection of intrinsic signals of suspended sediments. Therefore, we investigated the spectral variability arising from the sediment and bottom using laboratory and field-scale experiments. In the laboratory experiment, we focused on measuring spectral characteristics of suspended sediment according to particle size and sediment type. The laboratory experiment was conducted under conditions of completely mixed sediment and non-bottom reflectance using a specially designed rotating horizontal cylinder. To investigate the effects of different channel bottoms under sediment-laden flow conditions, we performed sediment tracer tests in field-scale channels comprising sand and vegetated bottoms. Based on experimental datasets, we performed spectral analysis and multiple endmember spectral mixture analysis (MESMA) to quantify the effect of spectral variability of sediment and bottom on the relationship between hyperspectral data and SSC. The results showed that optimal spectral bands were precisely estimated under non-bottom reflectance conditions, and the effective wavelengths depended on the sediment type. The fine sediments had a higher backscattering intensity compared to the coarse sediments, and the reflectance difference according to the particle size difference increased as the SSC increased. However, in the field-scale experiment, the bottom reflectance substantially decreased the R2 in the relationship between the hyperspectral data and SSC. Nevertheless, MESMA can quantify the contribution of suspended sediment and bottom signals as fractional images. Moreover, the suspended sediment fraction had a clear exponential relationship with SSC in all cases. We conclude that MESMA-driven sediment fractions could be an important alternative for estimating SSC in shallow rivers, as it quantifies the contributions of each factor and then minimizes the bottom effect.

Mapping Fractional Vegetation Coverage across Wetland Classes of Sub-Arctic Peatlands Using Combined Partial Least Squares Regression and Multiple Endmember Spectral Unmixing

Vegetation communities play a key role in governing the atmospheric-terrestrial fluxes of water, carbon, nutrients, and energy. The expanse and heterogeneity of vegetation in sub-arctic peatland systems makes monitoring change at meaningful spatial resolutions and extents challenging. We use a field-collected spectral endmember reference library to unmix hyperspectral imagery and map vegetation coverage at the level of plant functional type (PFT), across three wetland sites in sub-arctic Alaska. This study explores the optimization and parametrization of multiple endmember spectral mixture analysis (MESMA) models to estimate coverage of PFTs across wetland classes. We use partial least squares regression (PLSR) to identify a parsimonious set of critical bands for unmixing and compare the reference and modeled coverage. Unmixing, using a full set of 110-bands and a smaller set of 4-bands, results in maps that effectively discriminate between PFTs, indicating a small investment in fieldwork results in maps mirroring the true ground cover. Both sets of spectral bands differentiate between PFTs, but the 4-band unmixing library results in more accurate predictive mapping with lower computational cost. Reducing the unmixing reference dataset by constraining the PFT endmembers to those identified in the field-site produces only a small advantage for mapping, suggesting extensive fieldwork may not be necessary for MESMA to have a high explanatory value in these remote environments.

Monitoring shifting cultivation in Laos with Landsat time series

Shifting cultivation is an agricultural practice in which plots of land are cultivated temporarily, then abandoned, and vegetation is allowed to regenerate during fallow periods. Shifting cultivation is usually associated with cutting and burning forests and thus it is an important driver of forest disturbance in the tropics. However, studies of shifting cultivation are limited, and current area estimates of shifting cultivation are highly uncertain. Although Southeast Asia is a hotspot of shifting cultivation, there are no national maps of shifting cultivation in Southeast Asia at moderate or high resolution (less than or equal to 30 m). Monitoring shifting cultivation is challenging because it is highly dynamic, small-scale and results in complex post-disturbance landscapes. In this study, we monitored shifting cultivation using Landsat time series on Google Earth Engine for the entire country of Laos from 1991 to 2020. First, CCDC-SMA (Continuous Change Detection and Classification - Spectral Mixture Analysis) was used to detect forest disturbances. Then, these disturbances were attributed by combining time series analysis, object-based image analysis (OBIA), and post-disturbance land cover classification. Forest disturbances were assigned to Shifting cultivation, New plantation, Deforestation, Severe Drought, and Subtle Disturbance annually from 1991 to 2020 at a 30-m resolution. The major forest disturbances in 1991–2020 were mapped with an overall accuracy of 85%. Shifting cultivation is mapped with a producer's accuracy of 88% and a user's accuracy of 80%. The margin of error of the sampling-based area estimates of Shifting cultivation is 5.9%. Shifting cultivation is the main land use in Laos, accounting for 32.9% ± 1.9% of Laos over the past 30 years. To study changes in shifting cultivation over time, the area of shifting cultivation was estimated at 5-year intervals between 1991 and 2020 with all margins of error <17%. Results show that the area of slash-and-burn activities in Laos increased in 2015–2020. Our study provides an effective approach for monitoring shifting cultivation, which can be potentially applied into other regions. Our results not only provide valuable information for land management in Laos, but also can support analysis of spatial-temporal patterns of shifting cultivation and estimation of carbon emissions associated with shifting cultivation for REDD+ reporting.

A novel approach towards continuous monitoring of forest change dynamics in fragmented landscapes using time series Landsat imagery

Carbon emissions from forest ecosystems are greatly impacted by the acceleration of fragmentation and edge effects. Understanding these effects requires accurate monitoring of changes in fragmented forest landscapes. However, these changes are often low-intensity and small-scale, making it difficult to detect them using medium spatial resolution satellite images (e.g., Landsat). To address this challenge, this study developed the Pure Forest Index (PFI), which uses a combination of the existing vegetation index (VI) and spectral mixture analysis (SMA) to more effectively detect and characterize the contribution of forests to the observed spectral response of a pixel. The PFI was applied to detect forest changes in the Amazon rainforest from 1986 to 2020 using the Continuous Change Detection and Classification (CCDC) algorithm (hereafter referred to as the CCDC-PFI algorithm). The results showed reliable performance in mapping forest changes, with an overall accuracy of 0.94 (±0.03) at the spatial scale and a temporal accuracy of 91.1 % (within a two-year window). Comparison with other indices revealed that the PFI improves the ability to monitor forest dynamics with an increased overall accuracy of 0.02–0.35. The PFI also demonstrated advantages in enhancing sub-pixel forest information and suppressing non-forest backgrounds in various scenes compared to conventional VIs. The proposed approach is expected to benefit further research on forests and ecosystems.

Early-Season Mapping of Johnsongrass (Sorghum halepense), Common Cocklebur (Xanthium strumarium) and Velvetleaf (Abutilon theophrasti) in Corn Fields Using Airborne Hyperspectral Imagery

Accurate information on the spatial distribution of weeds is the key to effective site-specific weed management and the efficient and sustainable use of weed control measures. This work focuses on the early detection of johnsongrass, common cocklebur and velvetleaf present in a corn field using high resolution airborne hyperspectral imagery acquired when corn plants were in a four to six leaf growth stage. Following the appropriate radiometric and geometric corrections, two supervised classification techniques, such as spectral angle mapper (SAM) and spectral mixture analysis (SMA) were applied. Two different procedures were compared for endmember selections: field spectral measurements and automatic methods to identify pure pixels in the image. Maps for both, overall weeds and for each of the three weed species, were obtained with the different classification methods and endmember sources. The best results were achieved by defining the endmembers through spectral information collected with a field spectroradiometer. Overall accuracies ranged between 60% and 80% using SAM for maps that do not differentiate the weed species while it decreased to 52% when the three weed species were individually classified. In this case, the SMA classification technique clearly improved the SAM results. The proposed methodology shows it to be a promising prospect to be applicable to low cost images acquired by the new generation of hyperspectral sensors onboard unmanned aerial vehicles (UAVs).

Spectral Mixture Modeling of an ASTER Bare Soil Synthetic Image Using a Representative Spectral Library to Map Soils in Central-Brazil

Pedological maps in suitable scales are scarce in most countries due to the high costs involved in soil surveying. Therefore, methods for surveying and mapping must be developed to overpass the cartographic material obtention. In this sense, this work aims at assessing a digital soil map (DSM) built by multispectral data extrapolation from a source area to a target area using the ASTER time series modeling technique. For that process, eight representative toposequences were established in two contiguous micro-watersheds, with a total of 42 soil profiles for analyses and classification. We found Ferralsols, Plinthosols, Regosols, and a few Cambisols, Arenosols, Gleisols, and Histosols, typical of tropical regions. In the laboratory, surface soil samples were submitted to spectral readings from 0.40 µm to 2.50 µm. The soil spectra were morphologically interpreted, identifying shapes and main features typical of tropical soils. Soil texture grouped the curves by cluster analysis, forming a spectral library (SL). In parallel, an ASTER time series (2001, 2004, and 2006) was processed, generating a bare soil synthetic soil image (SySI) covering 39.7% of the target area. Multiple Endmember Spectral Mixture Analysis modeled the SL on the SySI generating DSM with 73% of Kappa index, in which identified about 77% is covered by rhodic Ferralsols. Besides the overestimation, the DSM represented the study area’s pedodiversity. Given the discussion raised, we consider including subsoil data and other features using other sensors in operations modeled by machine learning algorithms to improve results.

Exploring the characteristics and driving forces of orchard expansion in ecological fragile region: A case study of three typical counties in the Loess Plateau

The Loess Plateau exemplifies the type of ecologically fragile region that faces severe poverty challenges in China. Orchards have expanded rapidly over the past few decades and now constitute a considerable part of local economy. Not only do the characteristics of orchard expansion affect local economic development, but also exert additional pressure on the ecological environment. Therefore, it is essential for sustainable development on the Loess Plateau to investigate the characteristics and driving forces of orchard expansion. The Fuxian, Luochuan, Huangling, three typical orchard planting counties were chosen as the study area. Firstly, the orchard was extracted from the land use/cover classification from 1990–2020. It broadens the research approach to the identification of expansion cash crops by using the combination of linear spectral mixture analysis (LSMA) and decision tree. Secondly, the spatiotemporal dynamics of orchard expansion were quantitatively investigated based on spatial geometry center shift, physical geographical features, landscape pattern and orchard planting suitability. Then, we constructed an evaluation indicators system to detect the feature importance and partial dependence of different factors by random forest regression. It is more innovative to employ the machine learning method to investigate driving forces. Finally, the linkages between planting suitability and orchard expansion were further discussed, and subsequent policies were proposed. Findings demonstrated the orchard had continuously expanded over the past 30 years, with the fastest expansion rate during 1990–2005. Increased cohesion was accompanied by a shift in the orchard’s spatial distribution to the north central region and highly suitable planting regions. Slope turned out to be the primary factor affecting the orchard expansion. In the future, regions with aging orchard but high planting suitability should be the preferred choice for orchard expansion. Additionally, the transportation connectivity and governmental assistance are crucial considerations for the future planning of the orchard.

Characterizing Tree Species in Northern Boreal Forests Using Multiple-Endmember Spectral Mixture Analysis and Multi-Temporal Satellite Imagery

Northern boreal forests are characterized by open stands whereby trees, understory background, and shadow are all significant components of the spectral response within a pixels’ spatial footprint. To overcome this mixed pixel problem, accurate spectral characterization of these (endmember) components is necessary for spectral mixture analysis (SMA) to generate forest classifications at the species level. Obtaining these endmember spectra in the field, however, can be difficult or impossible. This study examined whether image endmember spectra can be identified using forest inventory information to derive dominant tree species classifications. This was tested using multiple-endmember SMA (MESMA) and single- and multi-date Landsat imagery of a forested area in the Northwest Territories, Canada. Image classifications (n = 80) were generated based on 20 image-date combinations and four unmixing models. Accuracies of 80% and 82% were achieved for open and medium dense forest stands, respectively using multi-date imagery, which outperformed single-date imagery acquired at peak phenology. The overall accuracy is 72%; lower due to challenges in very open stands. The multi-date MESMA approach was robust for both compositionally pure and mixed stands. The approach merits further investigation, particularly within the context of the increasing availability of regional-scale satellite imagery enabling composite time-series and spectral-temporal image features.

Estimation of boreal forest floor lichen cover using hyperspectral airborne and field data

Lichens are sensitive to competition from vascular plants, intensive silviculture, pollution and reindeer and caribou grazing, and can therefore serve as indicators of environmental changes. Hyperspectral remote sensing data has been proved promising for estimation of plant diversity, but its potential for forest floor lichen cover estimation has not yet been studied. In this study, we investigated the use of hyperspectral data in estimating ground lichen cover in boreal forest stands in Finland. We acquired airborne and in situ hyperspectral data of lichen-covered forest plots, and applied multiple endmember spectral mixture analysis to estimate the fractional cover of ground lichens in these plots. Estimation of lichen cover based on in situ spectral data was very accurate (coefficient of determination (r2) 0.95, root mean square error (RMSE) 6.2). Estimation of lichen cover based on airborne data, on the other hand, was fairly good (r2 0.77, RMSE 11.7), but depended on the choice of spectral bands. When the hyperspectral data were resampled to the spectral resolution of Sentinel-2, slightly weaker results were obtained. Tree canopy cover near the flight plots was weakly related to the difference between estimated and measured lichen cover. The results also implied that the presence of dwarf shrubs could influence the lichen cover estimates.

Linear spectral mixture analysis of land cover for assessment level sub-pixel using PlanetScope imagery in Dieng Plateau

Information on the land cover is essential as thematic information for planning, controlling, and spatial planning to create sustainable development. Remote sensing is a tool used to solve a problem related to space, environment, and zoning. One of the obstacles in using remote sensing data is the presence of mixed pixels. This research was conducted in the Dieng Plateau. This research aims to calculate accuracy assessment and land cover map fraction using PlanetScope imagery in Dieng Plateau. The remote sensing image is PlanetScope, recorded November 19, 2020. Topographic correction is carried out using the cosine correction method. The Linear Spectral Mixture Analysis (LSMA) method determines each endmember percentage land cover fraction. The field survey was conducted with 74 samples for accuracy testing. Each sample plot measures 10 m x 10 m. The topographic correction results can significantly affect land cover classification results. The result of the LSMA method classification used PlanetScope images to determine the percentage land cover map fraction of bare soil, impervious surface, vegetation, and water in one pixel with an accuracy of MAE 99.76%.

Hazardous and Noxious Substances (HNSs) Styrene Detection Using Spectral Matching and Mixture Analysis Methods

Hazardous and Noxious Substances (HNSs) Styrene Detection Using Spectral Matching and Mixture Analysis Methods