OLI Imagery Research Articles

Monitoring the 3-year thermal signatures of the Calbuco pre-volcano eruption event

The use of remote sensing to monitor volcanic eruption may not be very accurate. In this paper, we seek to describe supportive techniques to aid the efficiency of remote sensing in monitoring and predicting eruptions. The last three volcano eruptions in Calbuco occurred in 1961, 1976, and 2015. Calbuco is located on latitude 41.33 S and longitude 72.62 W. The duration of the research is 3 years before the eruption, that is, 1958–1960, 1973–1975, and 2012–2014. The specified duration was examined using the thermographic model and k factor analysis that is aided by the Global Land Data Assimilation System (GLDAS), Landsat 8 OLI, Mosaic, and ETM imageries. This study adopts the thermal analysis parameters which includes average surface temperature, ground heat flux, latent heat flux, sensible heat flux, surface temperature at ground layer 3, surface temperature at ground layer 10, net longwave temperature, and net shortwave radiation. The combination of remotely sensed measurement with the chosen techniques corroborates each other with salient discoveries like the k factor properties, the period of thermal signature retrieval from either the satellite and ground observations or the cup-like ripple effect whose base is found at the lineament beyond the volcanic site.

Mapping orangutan habitat and agricultural areas using Landsat OLI imagery augmented with unmanned aircraft system aerial photography

ABSTRACTConservation of the Sumatran orangutans’ (Pongo abelii) habitat is threatened by change in land use/land cover (LULCC), due to the logging of its native primary forest habitat, and the primary forest conversion to oil palm, rubber tree, and coffee plantations. Frequent LULCC monitoring is vital to rapid conservation interventions. Due to the costs of high-resolution satellite imagery, researchers are forced to rely on cost-free sources (e.g. Landsat), those, however, provide images at a moderate-to-low resolution (e.g. 15–250 m), permitting identification only general LULC classes, and limit the detection of small-scale deforestation or degradation. Here, we combine Landsat imagery with very high-resolution imagery obtained from an unmanned aircraft system (UAS). ​The UAS imagery was used as ‘drone truthing’ data to train image classification algorithms. Our results show that UAS data can successfully be used to help discriminate similar land-cover/use classes (oil palm plantation vs. reforestation vs. logged forest) with consistently high identification of over 75% on the generated thematic map, where the oil palm detection rate was as high as 89%. Because UAS is employed increasingly in conservation proWjects, this approach can be used in a large variety of them to improve land-cover classification or aid-specific mapping needs.

Wheat Monitoring by Using Kernel Based Possibilistic c-Means Classifier: Bi-sensor Temporal Multi-spectral Data

The existence of mixed pixels in the satellite images has always been an area of concern. Adding to the challenge is an occurrence of non-linearity between the classes, which is generally overlooked. The study makes an attempt to solve the two frequently occurring problems by kernel based fuzzy approach. This research work deals with Possibilistic c-Means (PCM) classifier with local, global, spectral angle and hyper tangent kernels for wheat crop (Triticum aestivum) identification in Haridwar, Uttarakhand, India. The multi-temporal vegetation index data of Formosat-2 have been used which covers the whole phenology of wheat crop. The additional sensor Landsat-8 OLI imagery has been filled the crucial gap of Formosat-2 temporal datasets. Nine types of proposed kernels based PCM classifier have been applied on three temporal datasets (four, five and six date combinations) to classify two classes early sown and late sown wheat crop. These test results have been concluded that at optimized weighted constant KMOD and polynomial kernel was found effective to separate wheat crop. The five and six date combination were sufficient to discriminate early sown and late sown wheat crop.

Impact of Land Use/Land Cover Change on Surface Temperature Condition of Awka Town, Nigeria

This paper is aimed at identifying the land use/cover types in Awka in relation to their temporal dynamics, the extent of land use change in the city and effects of land use change on surface temperature. Multitemporal Landsat TM, ETM+ and OLI imageries were obtained at 15 years interval for 1986, 2000 and 2015 respectively. Image classification was conducted using supervised classification method. The result showed that built-up area has been on the increase, expanding from 9.55 sqkm in 1986 to 21.3 sqkm in 2000 and 21.45 sqkm in 2015. Cultivated lands have maintained a steady decline since 2000 having lost about 3.29 sqkm of its area. Similarly, vegetation, made up of dense, savanna and riparian, has been on a decline from a total of 33.69sqkm in 1986 to 21.407 sqkm losing about 12.29 sqkm of its area and increased by a mere 4.07 sqkm in 2015. These alterations had given rise to an average increase of 2.2°C in surface radiant temperature. This study recommends that relevant government planning agencies (ACTDA, ASHDC, etc.) should factor in the concept of greening and green spaces into their development policies and strategies to ensure that fair, conducive microclimate and sustainable environment is maintained in the Awka urban area.

Soil erosion and its correlation with vegetation cover: An assesment using multispectral imagery and pixel-based geographic information system in Gesing Sub-Watershed, Central Java, Indonesia

Soil erosion in caused by five factors: rainfall erosivity, soil erodibility, slope and slope length, crop management, and land conservation practices. In theory, vegetation as one of the affecting factors has inversed correlation with soil erosion. This research is aimed to: (1) model RUSLE using pixel-based GIS, and (2) prove whether or not vegetation really has the said correlation with the soil erosion that occurs in Gesing Watershed. The method used in this research is divided into two: the use of RUSLE to estimate the soil erosion rate; and the use of fractional vegetation cover (FVC) formula to estimate the vegetation density in the area. Both methods used Landsat-8 OLI imagery, which is used to extract the RUSLE parameters as well as to derive the vegetation density through NDVI, and pixel-based GIS. The mapping of soil erosion rate distribution done in this research demonstrated that pixel-based modeling is able to represent a much more detailed and logical distribution of a phenomenon. The distribution of soil erosion rate in Gesing Watershed showed that the erosion rate in this area is relatively minor. About 1425.99 hectares and 1587.57 hectares of the total area have erosion rate of 0 – 15 tons/ha/yr (very mild) and 15 – 60 tons/ha/yr (mild) respectively.

Atmospheric Correction of Satellite GF-1/WFV Imagery and Quantitative Estimation of Suspended Particulate Matter in the Yangtze Estuary.

The Multispectral Wide Field of View (WFV) camera on the Chinese GF-1 satellite, launched in 2013, has advantages of high spatial resolution (16 m), short revisit period (4 days) and wide scene swath (800 km) compared to the Landsat-8/OLI, which make it an ideal means of monitoring spatial-temporal changes of Suspended Particulate Matter (SPM) in large estuaries like the Yangtze Estuary. However, a lack of proper atmospheric correction methods has limited its application in water quality assessment. We propose an atmospheric correction method based on a look up table coupled by the atmosphere radiative transfer model (6S) and the water semi-empirical radiative transfer (SERT) model for inversion of water-leaving reflectance from GF-1 top-of-atmosphere radiance, and then retrieving SPM concentration from water-leaving radiance reflectance of the Yangtze Estuary and its adjacent sea. Results are validated by the Landsat-8/OLI imagery together with autonomous fixed station data, and influences of human activities (e.g., waterway construction and shipping) on SPM distribution are analyzed.

Mapping Distinct Forest Types Improves Overall Forest Identification Based on Multi-Spectral Landsat Imagery for Myanmar’s Tanintharyi Region

We investigated the use of multi-spectral Landsat OLI imagery for delineating mangrove, lowland evergreen, upland evergreen and mixed deciduous forest types in Myanmar’s Tanintharyi Region and estimated the extent of degraded forest for each unique forest type. We mapped a total of 16 natural and human land use classes using both a Random Forest algorithm and a multivariate Gaussian model while considering scenarios with all natural forest classes grouped into a single intact or degraded category. Overall, classification accuracy increased for the multivariate Gaussian model with the partitioning of intact and degraded forest into separate forest cover classes but slightly decreased based on the Random Forest classifier. Natural forest cover was estimated to be 80.7% of total area in Tanintharyi. The most prevalent forest types are upland evergreen forest (42.3% of area) and lowland evergreen forest (21.6%). However, while just 27.1% of upland evergreen forest was classified as degraded (on the basis of canopy cover <80%), 66.0% of mangrove forest and 47.5% of the region’s biologically-rich lowland evergreen forest were classified as degraded. This information on the current status of Tanintharyi’s unique forest ecosystems and patterns of human land use is critical to effective conservation strategies and land-use planning.

Multi-temporal change detection of seagrass beds using integrated Landsat TM/ETM +/OLI imageries in Cam Ranh Bay, Vietnam

Seagrass beds comprise a unique marine ecosystem that acts as a biofilter in marine environments and serves as a spawning ground and nursery for various species of fish. Long-term monitoring of seagrass beds is critical to understanding the dynamic relationships between the ecosystems and the stresses from natural systems and society. This study investigated temporal changes of seagrass beds in Cam Ranh Bay (CRB), Vietnam using multi-temporal Landsat data from 1996 to 2015. The data were processed through 5 main steps including: (1) image preprocessing to convert Landsat data to the top of atmosphere reflectance (TOA) and to correct atmospheric effects, (2) water column correction to eliminate effects on remotely sensed data of aquatic environments, (3) image classification using a linear mixed model, (4) accuracy assessment using the ground reference data, and (5) change detection of seagrass beds. The classification results compared with the ground reference data indicated that the overall accuracies and Kappa coefficients were higher than 91.7% and 0.8, respectively, in all cases. From 1996 to 2015, the total area of seagrass beds had declined by approximately 25% (66ha), mainly attributed to coastal development and infrastructure construction.

Automated Subpixel Surface Water Mapping from Heterogeneous Urban Environments Using Landsat 8 OLI Imagery

Water bodies are a fundamental element of urban ecosystems, and water mapping is critical for urban and landscape planning and management. Remote sensing has increasingly been used for water mapping in rural areas; however, when applied to urban areas, this spatially- explicit approach is a challenging task due to the fact that the water bodies are often of a small size and spectral confusion is common between water and the complex features in the urban environment. Water indexes are the most common method of water extraction at the pixel level. More recently, spectral mixture analysis (SMA) has been widely employed in analyzing the urban environment at the subpixel level. The objective of this study is to develop an automatic subpixel water mapping method (ASWM) which can achieve a high accuracy in urban areas. Specifically, we first apply a water index for the automatic extraction of mixed land-water pixels, and the pure water pixels that are generated in this process are exported as the final result. Secondly, the SMA technique is applied to the mixed land-water pixels for water abundance estimation. As for obtaining the most representative endmembers, we propose an adaptive iterative endmember selection method based on the spatial similarity of adjacent ground surfaces. One classical water index method (the modified normalized difference water index (MNDWI)), a pixel-level target detection method (constrained energy minimization (CEM)), and two widely used SMA methods (fully constrained least squares (FCLS) and multiple endmember spectral mixture analysis (MESMA)) were chosen for the water mapping comparison in the experiments. The results indicate that the proposed ASWM was able to detect water pixels more efficiency than other unsupervised water extraction methods, and the water fractions estimated by the proposed ASWM method correspond closely to the reference fractions with the slopes of 0.97, 1.02, 1.04, and 0.98 and the R-squared values of 0.9454, 0.9486, 0.9665, and 0.9607 in regression analysis corresponding to different test regions. In the quantitative accuracy assessment, the ASWM method shows the best performance in water mapping with the mean kappa coefficient of 0.862, mean producer’s accuracy of 82.8%, and mean user’s accuracy of 91.8% for test regions.

Landsat-8 imagery to estimate clarity in near-shore coastal waters: Feasibility study - Chabahar Bay, Iran

This study examined the advantages of incorporating the new band of Landsat-8 OLI imagery (band 1: Coastal/Aerosol, 435–451nm) to a model for estimation of Secchi disk depth (SDD) values (as an indicator for transparency) in near-shore coastal waters using multispectral bands. In doing so, Chabahar Bay in the southern part of Iran (north of Gulf of Oman) was selected as the study area. Two approximately four-hour in-situ observations (including 48 and 56 field measured SDD values for each date respectively) were performed in the study area using Secchi disk; this was designed to start about two hours before and end about two hours after the time of satellite overpasses. Thereafter, a model was formed for estimation of SDD values based on the terms including all possible linear and mutual ratio values of Coastal/Aerosol (B1), Blue (B2), Green (B3), and Red bands (B4). In the first step, the correlation between reflectance/ratio reflectance values of these bands and Ln(SDD) values were calculated to indicate higher correlated bands/band ratios with the first field measured SDD values. Consequently, 17 combinations of highest correlated bands/band ratios were selected to estimate SDD values. In this regard, 32 points among the 48 field observations were selected to determine unknown coefficients of models using a multiple linear regression, and the rest 16 points were designated for accuracy assessment the results. Eventually, the measured SDD values in second field observations were utilized for validating the results. Final results demonstrated that combination of linear terms including B1, B2 and B3 bands and band ratio terms including ratio reflectance values of B4/B3, B3/B1, and B2/B1 has led to obtain the highest accuracy (R2=0.866 and RMSE=0.919, SVM feature weight=4.294). This was in agreement with the results obtained from the second observations. Finally, by applying the entire 104 field observed SDD values, the model in form of SDD=0.077exp(1.209RB1−1.739RB2+0.412RB3−5.198RB3/RB1+10.408RB2/RB1) can be used to determine SDD values in near-shore coastal waters of Chabahar Bay using atmospherically corrected reflectance values of Landsat-8 OLI bands.

ANALYSIS OF RELATIONSHIP BETWEEN URBAN HEAT ISLAND EFFECT AND LAND USE/COVER TYPE USING LANDSAT 7 ETM+ AND LANDSAT 8 OLI IMAGES

The main objectives of this study are (i) to calculate Land Surface Temperature (LST) from Landsat imageries, (ii) to determine the UHI effects from Landsat 7 ETM+ (June 5, 2001) and Landsat 8 OLI (June 17, 2014) imageries, (iii) to examine the relationship between LST and different Land Use/Land Cover (LU/LC) types for the years 2001 and 2014. The study is implemented in the central districts of Antalya. Initially, the brightness temperatures are retrieved and the LST values are calculated from Landsat thermal images. Then, the LU/LC maps are created from Landsat pan-sharpened images using Random Forest (RF) classifier. Normalized Difference Vegetation Index (NDVI) image, ASTER Global Digital Elevation Model (GDEM) and DMSP_OLS nighttime lights data are used as auxiliary data during the classification procedure. Finally, UHI effect is determined and the LST values are compared with LU/LC classes. The overall accuracies of RF classification results were computed higher than 88 % for both Landsat images. During 13-year time interval, it was observed that the urban and industrial areas were increased significantly. Maximum LST values were detected for dry agriculture, urban, and bareland classes, while minimum LST values were detected for vegetation and irrigated agriculture classes. The UHI effect was computed as 5.6 °C for 2001 and 6.8 °C for 2014. The validity of the study results were assessed using MODIS/Terra LST and Emissivity data and it was found that there are high correlation between Landsat LST and MODIS LST data (r<sup>2</sup> = 0.7 and r<sup>2</sup> = 0.9 for 2001 and 2014, respectively).

ANALYSIS OF RELATIONSHIP BETWEEN URBAN HEAT ISLAND EFFECT AND LAND USE/COVER TYPE USING LANDSAT 7 ETM+ AND LANDSAT 8 OLI IMAGES

Abstract. The main objectives of this study are (i) to calculate Land Surface Temperature (LST) from Landsat imageries, (ii) to determine the UHI effects from Landsat 7 ETM+ (June 5, 2001) and Landsat 8 OLI (June 17, 2014) imageries, (iii) to examine the relationship between LST and different Land Use/Land Cover (LU/LC) types for the years 2001 and 2014. The study is implemented in the central districts of Antalya. Initially, the brightness temperatures are retrieved and the LST values are calculated from Landsat thermal images. Then, the LU/LC maps are created from Landsat pan-sharpened images using Random Forest (RF) classifier. Normalized Difference Vegetation Index (NDVI) image, ASTER Global Digital Elevation Model (GDEM) and DMSP_OLS nighttime lights data are used as auxiliary data during the classification procedure. Finally, UHI effect is determined and the LST values are compared with LU/LC classes. The overall accuracies of RF classification results were computed higher than 88 % for both Landsat images. During 13-year time interval, it was observed that the urban and industrial areas were increased significantly. Maximum LST values were detected for dry agriculture, urban, and bareland classes, while minimum LST values were detected for vegetation and irrigated agriculture classes. The UHI effect was computed as 5.6 °C for 2001 and 6.8 °C for 2014. The validity of the study results were assessed using MODIS/Terra LST and Emissivity data and it was found that there are high correlation between Landsat LST and MODIS LST data (r2 = 0.7 and r2 = 0.9 for 2001 and 2014, respectively).

Canopy cover estimation in miombo woodlands of Zambia: Comparison of Landsat 8 OLI versus RapidEye imagery using parametric, nonparametric, and semiparametric methods

Acquiring forest resources information for tropical developing countries is challenging due to financial and logistical constraints. Yet, this information is critical for enhancing management capability and engaging in international initiatives such as Reducing Emissions from Deforestation and forest Degradation (REDD +). The use of multi-source inventories (i.e., remote-sensing, field, and other data) in integrated models has shown increasing promise for accurately estimating forest attributes at lower costs. In this study, we compared the use of Landsat 8 OLI versus RapidEye satellite imagery in four modeling approaches (generalized linear model (GLM), generalized additive model (GAM), k-Nearest Neighbors (k-NN), Random Forests), with and without auxiliary information (e.g., soils characteristics, distance to roads, etc.) to estimate percent canopy cover by pixel for an ~ 1,000,000 ha area in Zambia. We derived plot-level canopy cover as the dependent variable, using field-measured data collected according to current National Forest Inventory (NFI) protocol. Using cross-validation statistics, Landsat 8 OLI exhibited better results than RapidEye across modeling approaches likely due to the additional short-wave infrared bands which consistently improved model performance (average root mean squared prediction error = 10.1% versus 11.0%). The GAM approach was more precise, though more challenging to fit. For both remote sensing data sources and all modeling approaches, other auxiliary information improved the model; soil variables were commonly selected for inclusion using a Genetic Algorithm. Using a binomial GAM with Landsat 8 OLI and soil variables, and by applying the current FAO forest/non-forest definition (i.e., canopy cover > 10% for a 0.5 ha area), we estimated the total forest area as 758,100 ha (95% bootstrapped confidence interval of ± 3,953 ha). Overall, our research indicates that sufficiently accurate forest area estimates for Zambia can be obtained using canopy cover GAM models that incorporate NFI data and freely-available remote sensing imagery and soil information.

Heterogeneity of glacial lake expansion and its contrasting signals with climate change in Tarim Basin, Central Asia

On the basis of Landsat TM/ETM +/OLI imagery in the years 1990, 2000 and 2013, changes of lake area were detected and its contrasting signals with climate change are addressed for Tarim Basin in Central Asia. During the past 23 years, the lake area has expanded at an average rate of 0.67 %/a, with the fastest rates in Altun Shan and Tian Shan mountains and slower rates in the Karakoram and Pamir, which indicates spatially heterogeneous warmer and wetter climatic signals in the basin. Examining decades, the average expansion rate of lake area (0.98 %/a) over 2000–2013 was about four times that (0.23 %/a) of 1990–2000, indicating accelerated warmer–wetter trends around the transition year 2000 in the mountain areas. Discrepant area expansion of different types of glacial lake implies contrasting signals of climate change in the Tarim Basin. Fewer direct climatic signals can be inferred from changes of supraglacial lakes. Ice-contacting lakes characterized by the fastest expansion rate (3.35 %/a) depict accelerated glacier shrinkage caused by climate warming. Non-glacier-fed lakes expansion at the rate of 0.57 %/a reflect an apparent increase of precipitation in the mountains of Tarim Basin.

An effective modified water extraction method for Landsat-8 OLI imagery of mountainous plateau regions

Water body extraction from remote sensing imagery is an efficient way to investigate and monitor water resources. In the study area of this research, a mountainous plateau near Kashgar, China, sparse vegetation and seasonal rivers affect water body extraction. In order to extract water bodies, a modified water body extraction method is proposed in this paper and tested using Landsat-8 OLI imagery. Following this method, binary images are first generated using a classification, a Tasseled Cap transform, and a normalized difference water index, respectively, and then combined to yield a mask. Next, water bodies are delineated by masking the Landsat-8 OLI imagery and then refined by eliminating false areas using a supervised classification. It is demonstrated from the resulting water body maps that terrain related shadows in imagery were effectively eliminated and river tributaries and artificial ditches were precisely delineated, with accuracy up to 94%. Compared with several current water body extraction methods, the modified method yielded water body maps with better visualization and slightly improved accuracy.

Comparing Landsat water index methods for automated water classification in eastern Australia

Abstract Automating the accurate classification of water in Landsat imagery will benefit many researchers conducting large-area multi-temporal analyses of the USGS archive. We propose that water index methods based on data normalised to surface reflectance, using thresholds optimised for a large selection of data, provide a simple yet accurate method for automated water classification across large regions. In order to select the best index for this task a comprehensive comparative analyses was required. We assessed the accuracy of seven water index methods for classifying water in 30 m resolution Landsat TM/ETM +/OLI imagery from eastern Australia. These indexes were the Automated Water Extraction Index for images with shadows (AWEIshadow) and without shadows (AWEIno shadow), tasselled cap wetness (TCWCrist), two variations of the normalised difference water index (NDWIMcFeeters and NDWIXu), a water index created using canonical variates analysis from top-of-atmosphere data (WI2006), and a new water index created with linear discriminant analysis from data processed to surface reflectance (WI2015). A wide variety of water (50,868), non-water (36,833) and mixed (16,499) validation pixels were selected from Landsat images across the states of New South Wales and Queensland. Water area and the colour of water and non-water features were determined for each validation pixel using coincident high resolution imagery and TM/ETM + reflectance. A single optimum threshold for classifying each index into water and non-water was determined using pure pixels. In general the WI2015, WI2006 and AWEIshadow performed the best, with all indexes achieving overall accuracies of 95–99% for pure pixels, and 73–75% for mixed pixels. Omission errors were more common than commission errors, and water area was usually underestimated, especially where water was green-brown in colour, and/or where water bodies were small or had long perimeters with many mixed pixels. The accuracy of each index was highly dependent on the composition of the validation pixels, with no index performing best across all water and non-water pixel types. All indexes and thresholds were found to perform consistently across images from the TM, ETM + and OLI sensors, facilitating the automated classification of water to similar levels of accuracy for the growing archive of Landsat data.

Mapping paddy rice planting area in rice-wetland coexistent areas through analysis of Landsat 8 OLI and MODIS images

Accurate and up-to-date information on the spatial distribution of paddy rice fields is necessary for the studies of trace gas emissions, water source management, and food security. The phenology-based paddy rice mapping algorithm, which identifies the unique flooding stage of paddy rice, has been widely used. However, identification and mapping of paddy rice in rice-wetland coexistent areas is still a challenging task. In this study, we found that the flooding/transplanting periods of paddy rice and natural wetlands were different. The natural wetlands flood earlier and have a shorter duration than paddy rice in the Panjin Plain, a temperate region in China. We used this asynchronous flooding stage to extract the paddy rice planting area from the rice-wetland coexistent area. MODIS Land Surface Temperature (LST) data was used to derive the temperature-defined plant growing season. Landsat 8 OLI imagery was used to detect the flooding signal and then paddy rice was extracted using the difference in flooding stages between paddy rice and natural wetlands. The resultant paddy rice map was evaluated with in-situ ground-truth data and Google Earth images. The estimated overall accuracy and Kappa coefficient were 95% and 0.90, respectively. The spatial pattern of OLI-derived paddy rice map agrees well with the paddy rice layer from the National Land Cover Dataset from 2010 (NLCD-2010). The differences between RiceLandsat and RiceNLCD are in the range of ±20% for most 1-km grid cell. The results of this study demonstrate the potential of the phenology-based paddy rice mapping algorithm, via integrating MODIS and Landsat 8 OLI images, to map paddy rice fields in complex landscapes of paddy rice and natural wetland in the temperate region.

Predicting relative species composition within mixed conifer forest pixels using zero-inflated models and Landsat imagery

Abstract Ecological and land management applications would often benefit from maps of relative canopy cover of each species present within a pixel, instead of traditional remote-sensing based maps of either dominant species or percent canopy cover without regard to species composition. Widely used statistical models for remote sensing, such as randomForest (RF), support vector machines (SVM), and generalized linear regression (GLM), are problematic for this purpose as they often fail to properly predict the absence of a target species, especially in areas of high vegetation diversity, due to the relative abundance of absence observations (or zero values) in the reference data used to train predictive models. Experience has shown that RF, SVM, and GLM models trained on such reference data produce biased values of PCC, for example, in forested areas absent the target species, PCC is overestimated, while in forested areas where a target species PCC is abundant, PCC tends to be underestimated. We used zero-inflated regression modeling to reduce such bias and better predict PCC-by-species within each pixel in mixed conifer forests. Zero-inflated regression models use a two-step process to first predict the presence or absence of the target species, and then to predict continuous levels of PCC only where the target species is present. We compared the results of three widely used methods (RF, SVM, and GLM) to nine zero-inflated models for their ability to predict continuous PCC for each of five different conifer species in heterogeneous forests of northwestern Montana using Landsat TM and OLI imagery. Our best zero-inflated models resulted in a mean difference of − 3.84% to 2.26%, 95% confidence interval of 6.22% to 13.09%, and RMSE of 11.26% to 22.98%, depending on the species. The success of the zero-inflated model was robust across methods tested. Both the zero-inflated and traditional methods were successful in estimating continuous canopy cover, however, the traditional models showed a substantial bias by never correctly predicting the absence of the target species, while the zero-inflated models correctly predicted species absence 57% to 84% of the time, depending on the species. Visual inspection of the predicted maps compared to high-resolution imagery demonstrated that the zero-inflated models also more closely matched the landscape, as traditional models more often incorrectly predicted canopy cover in non-forested areas. Using the zero-inflated process dramatically reduced the bias of the results, allowing end users to make management decisions with increased confidence about where a target species is absent, something not possible with the traditional methods tested.

Mapping Spatial Distribution of Larch Plantations from Multi-Seasonal Landsat-8 OLI Imagery and Multi-Scale Textures Using Random Forests

The knowledge about spatial distribution of plantation forests is critical for forest management, monitoring programs and functional assessment. This study demonstrates the potential of multi-seasonal (spring, summer, autumn and winter) Landsat-8 Operational Land Imager imageries with random forests (RF) modeling to map larch plantations (LP) in a typical plantation forest landscape in North China. The spectral bands and two types of textures were applied for creating 675 input variables of RF. An accuracy of 92.7% for LP, with a Kappa coefficient of 0.834, was attained using the RF model. A RF-based importance assessment reveals that the spectral bands and bivariate textural features calculated by pseudo-cross variogram (PC) strongly promoted forest class-separability, whereas the univariate textural features influenced weakly. A feature selection strategy eliminated 93% of variables, and then a subset of the 47 most essential variables was generated. In this subset, PC texture derived from summer and winter appeared the most frequently, suggesting that this variability in growing peak season and non-growing season can effectively enhance forest class-separability. A RF classifier applied to the subset led to 91.9% accuracy for LP, with a Kappa coefficient of 0.829. This study provides an insight into approaches for discriminating plantation forests with phenological behaviors.

Mapping health levels of Robinia pseudoacacia forests in the Yellow River delta, China, using IKONOS and Landsat 8 OLI imagery

The largest artificial Robinia pseudoacacia forests in the Yellow River delta of China have been infected by dieback diseases. Over the past several decades, this has caused a large amount of morta...