Landsat Bands Research Articles

Automatic Mapping of Burned Areas Using Landsat 8 Time-Series Images in Google Earth Engine: A Case Study from Iran

Due to the natural conditions and inappropriate management responses, large part of plains and forests in Iran have been burned in recent years. Given the increasing availability of open-access satellite images and open-source software packages, we developed a fast and cost-effective remote sensing methodology for characterizing burned areas for the entire country of Iran. We mapped the fire-affected areas using a post-classification supervised method and Landsat 8 time-series images. To this end, the Google Earth Engine (GEE) and Google Colab computing services were used to facilitate the downloading and processing of images as well as allowing for effective implementation of the algorithms. In total, 13 spectral indices were calculated using Landsat 8 images and were added to the nine original bands of Landsat 8. The training polygons of the burned and unburned areas were accurately distinguished based on the information acquired from the Iranian Space Agency (ISA), Sentinel-2 images, and Fire Information for Resource Management System (FIRMS) products. A combination of Genetic Algorithm (GA) and Neural Network (NN) approaches was then implemented to specify 19 optimal features out of the 22 bands. The 19 optimal bands were subsequently applied to two classifiers of NN and Random Forest (RF) in the timespans of 1 January 2019 to 30 December 2020 and of 1 January 2021 to 30 September 2021. The overall classification accuracies of 94% and 96% were obtained for these two classifiers, respectively. The omission and commission errors of both classifiers were also less than 10%, indicating the promising capability of the proposed methodology in detecting the burned areas. To detect the burned areas caused by the wildfire in 2021, the image differencing method was used as well. The resultant models were finally compared to the MODIS fire products over 10 sampled polygons of the burned areas. Overall, the models had a high accuracy in detecting the burned areas in terms of shape and perimeter, which can be further implicated for potential prevention strategies of endangered biodiversity.

Temporal and spatial changes in soil organic carbon and soil inorganic carbon stocks in the semi-arid area of northeast China

Soil organic carbon (SOC) and soil inorganic carbon (SIC) has important effects on soil physical, chemical and biological properties. They play an important role in coordinating the relationship between soil water and air, increasing soil water holding capacity and improving plant productivity. In this study, a boosted regression trees (BRT) model was developed to map the spatial distribution carbon stocks in the semi-arid region of Northeast China in 1990 and 2015. During the two periods, 10-fold cross-validation technology was used to test the performance and uncertainty of BRT model. In order to construct the model, 9 environmental variables (derived from climate, topography and biology) and 173 (1990) and 223 (2015) topsoil (0–30 cm) samples were used. The comparison between estimated and observed data shows that the RMSE of SOC and SIC stocks were 0.53 kgm−2 and 0.19 kgm−2 in 1990, and 0.65 kgm−2 and 0.20 kgm−2 in 2015, respectively. Elevation, normalized difference vegetation index, mean annual precipitation and Landsat band 3 were identifies as critical environmental factors for simulating the spatial distribution of SOC, accounting for 76.6 % and 70.3 % of the total relative importance in 1990 and 2015, respectively. Mean annual precipitation, mean annual temperature and topographic wetness index were the critical environmental factors for simulating the spatial variation of SIC during the two periods. Land use change also played an important role in the spatial variability of SOC and SIC stocks. In the past 25 years, soil carbon stocks decreased from 6.2 kg m−2 in 1990 to 5.9 kg m−2 in 2015. The spatial distribution pattern of SOC was high in northeastern area and low in southwestern area during the two periods, while the spatial distribution pattern of SIC was opposite to that of SOC stocks. The mapped soil carbon stock distribution is fundamental to future study of soil carbon cycle and regional carbon balance in semi-arid regions.

Spatiotemporal and multi-sensor analysis of surface temperature, NDVI, and precipitation using google earth engine cloud computing platform

Vegetation, precipitation, and surface temperature are three important elements of the environment. By increasing the concerns about climate change and global warming, monitoring vegetation dynamics are considered to be crucial. In this study, the cross-relationship between vegetation, surface temperature, and precipitation, and their fluctuations over the past 21 years are evaluated. Day time LST from Terra sensor of MODIS, nir and red bands of Landsat 7 ETM+ and Landsat 8 OLI, and Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS) are used in this research. Data were evaluated and processed using the google earth engine cloud processing platform. According to the results, it was concluded that the correlations between the annual average of normalized difference vegetation index and precipitation are not significant. Evaluation of the cross-seasonal correlations exhibited the availability of the strong and significant correlation with a value of r2 = 0.82 between vegetation thickness and precipitation, during the spring and summer, especially from April to August. Moreover, surface temperature exposed an inverse correlation with precipitation and NDVI with the values of r2= 0.776 and r2= 0.68 respectively, these relationships are highly significant. According to the results of this study, vegetation declined sharply in particular years, and this decrease occurred due to insufficient rainfalls.

Above-Ground Biomass Estimation for Coniferous Forests in Northern China Using Regression Kriging and Landsat 9 Images

Accurate estimation of forest above-ground biomass (AGB) is critical for assessing forest quality and carbon stocks, which can improve understanding of the vegetation growth processes and the global carbon cycle. Landsat 9, the latest launched Landsat satellite, is the successor and continuation of Landsat 8, providing a highly promising data resource for land cover change, forest surveys, and terrestrial ecosystem monitoring. Regression kriging was developed in the study to improve the AGB estimation and mapping using the Landsat 9 image in Wangyedian forest farm, northern China. Multiple linear regression (MLR), support vector machine (SVM), back propagation neural network (BPNN), and random forest (RF) were used as the original models to predict the AGB trends, and the optimal model was used to overlay the results of kriging interpolation based on the residuals to obtain the new AGB predictions. In addition, Landsat 8 images in Wangyedian were used for comparison and verification with Landsat 9. The results showed that all bands of Landsat 8 and Landsat 9 maintained a high degree of uniformity, with positive correlation coefficients ranging from 0.77 to 0.89 (p < 0.01). RF achieved the highest estimation accuracy among all the original models based on the two data sources. However, kriging regression can significantly reduce the estimation error, with the root mean square error (RMSE) decreasing by 55.4% and 51.1%, for Landsat 8 and Landsat 9, respectively, compared to the original RF. Further, the R2 and the lowest RMSE for Landsat 8 were 0.88 and 16.83 t/ha, while, for Landsat 9, they were 0.87 and 17.91 t/ha. The use of regression kriging combined with Landsat 9 imagery has great potential for achieving efficient and highly accurate forest AGB estimates, providing a new reference for long-term monitoring of forest resource dynamics.

A Comparison of Machine Learning and Geostatistical Approaches for Mapping Forest Canopy Height over the Southeastern US Using ICESat-2

The availability of canopy height information in the Ice, Cloud, and Land Elevation Satellite-2’s (ICESat-2’s) land and vegetation product, or ATL08, presents opportunities for developing full-coverage products over broad spatial scales. The primary goal of this study was to develop a 30-meter canopy height map over the southeastern US, for the Southeastern Plains ecoregion and the Middle Atlantic Coastal Plains ecoregion. More specifically, this work served to compare well-known modeling approaches for upscaling canopy information from ATL08 to develop a wall-to-wall product. Focusing on only strong beams from nighttime acquisitions, the h_canopy parameter was extracted from ATL08 data. Landsat-8 bands and derived vegetation indices (normalized difference vegetation index, enhanced vegetation index, and modified soil-adjusted vegetation index) along with National Land Cover Database’s canopy cover and digital elevation models were used to extrapolate ICESat-2 canopy height from tracks to the regional level. Two different modeling techniques, random forest (RF) and regression kriging (RK), were applied for estimating canopy height. The RF model estimated canopy height with a coefficient of determination (R2) value of 0.48, root-mean-square error (RMSE) of 4.58 m, mean absolute error (MAE) of 3.47 and bias of 0.23 for independent validation, and an R2 value of 0.38, RMSE of 6.39 m, MAE of 5.04 and bias of −1.39 when compared with airborne lidar-derived canopy heights. The RK model estimated canopy heights with an R2 value of 0.69, RMSE of 3.49 m, MAE of 2.61 and bias of 0.03 for independent validation, and an R value of 0.68, R2 value of 0.47, RMSE of 5.96m, MAE of 4.52 and bias of −1.81 when compared with airborne lidar-derived canopy heights. The results suggest feasibility for the implementation of the RK method over a larger spatial extent and potential for combining other remote sensing and satellite data for future monitoring of canopy height dynamics.

Estimating soil moisture condition of paddy fields by using optical remote sensing imagery

Soil moisture is essential in monitoring agricultural lands, particularly in Jember, East Java which serves as one of Indonesian rice-producing regions. Scarcity of information related to the environment crucial to rice planting is evident. This includes detailed growth phase and soil moisture, where their estimation could be done through exploiting remote sensing data. This study aims to estimate soil moisture condition on paddy fields in selected study areas by applying Landsat 8 OLI/TIRS data, acquired in 2021. Thermal band of Landsat 8 was utilized to derive the Soil Moisture Index (SMI). This study also investigated the variation of vegetation index (studied using NDVI) and land surface temperature (LST) as parameters related to soil moisture conditions. Paddy fields in the study area were dominated by moderate soil moisture levels, with average SMI of 0.47, NDVI=0.45, and about 22°C temperature. The SMI ranged from 0.21 to 0.65. The low SMI values indicate low vegetation density and high surface temperature in paddy lands. This research suggested that SMI from Landsat 8 could serve as an efficient approach in monitoring soil moisture condition and understanding its correlation to surface temperature and vegetation condition in agricultural areas, particularly paddy fields.

Application of remote sensing techniques to identify iron ore deposits in the Central Eastern Desert, Egypt: a case study at Wadi Karim and Gabal El-Hadid areas

The integration of remote sensing, spectral measurements and field verification helped in discriminating new iron occurrences hosted in the metavolcanic rocks at Wadi Karim and Gabal El-Hadid areas in the Central Eastern Desert (CED) of Egypt. The iron host rocks were carefully recognized through different image processing techniques that were applied on Landsat-8 satellite image data with the implementation of the spectral signatures of the various iron minerals and host rocks. The detected iron ore is found in the form of Banded Iron Formation (BIF), veins and lenses of varied thicknesses ranging from a few centimetres to 5 m. They are composed mainly of magnetite and hematite, as well as accessories of aluminium, iron silicates and quartz. Moreover, the structure controls on iron ore occurrences were also illustrated in the investigated areas. The alignment of the iron forms with the primary and secondary structural planes of their host rocks may indicate the origin and mode of occurrence of the explored iron ore, as contemporaneous and syngenetic deposition with the solidification of the host metavolcanics. Several remote sensing techniques including Crosta principal component analysis (CPCA), constrained energy minimization (CEM) supervised classification technique and a newly proposed Landsat-8 band ratio (band6/band2) were applied for discriminating the iron-rich localities within the studied areas. These techniques showed high efficiency and applicability in the accurate delineation of the iron-enriched areas; this was validated through the field study.

Analysis of univariate linear, robust-linear, and non-linear machine learning algorithms for satellite-derived bathymetry in complex coastal terrain

The blue economic, maritime, and exploration activities rely on precise knowledge of coastal bathymetry. The recent trends in Satellite-Derived Bathymetry (SDB) research have focused on various methods of estimation using very high-resolution satellite imagery and in-situ data, but mostly in clear and transparent water. The Indian coastal region mostly has murky water, which is further constrained to employ SDB techniques in areas of river mouth and delta due to the presence of numerous underwater rocks and rich sediment carried by rivers. This study is focused on analyzing SDB in two study areas characterized as turbid, sediment-laden, and complex due presence of numerous underwater rocks. The objective of the research is to analyze and compare the performance of a few univariate Machine Learning (ML) regression algorithms in SDB estimation using ASTER, LANDSAT-8, and Sentinel-2A spectral bands with high resolution in-situ bathymetric data. This study evaluates linear, three robust linear Huber, RANSAC & ThielSen, and a non-linear Gaussian Process Regression ML algorithm, to analyze the efficacy in SDB estimation using a univariate spectral bandwidth of satellite imagery. The applied non-linear regression model has estimated SDB with the accuracy of R2 0.87, RMSE 1.77 m, and MAE 1.27 m for depth of 30 m in site A; and site B, R2 0.91, RMSE 1.51 m & MAE 1.17 m for depth of 22 m. The advantage offered by this approach includes; minimum required parameters, less processing time, and the potential to be an alternative to hydrographic surveys.

Research on joint inversion of volcanic shortwave infrared emissivity and temperature based on day and night images

ABSTRACT In order to solve the problem of inaccurate emissivity obtained by empirical or experimental measurements in traditional volcanic inversion methods, which leads to the discrepancy between the temperature inversion results and the actual temperature, this paper constructs a joint inversion model of volcanic temperature and emissivity, and solves the volcanic temperature and emissivity simultaneously from the image element scale.In order to obtain the two unknown parameters of volcanic temperature and emissivity simultaneously, the study image element is assumed to be a pure image element and Lambertian body, and based on the blackbody radiation law and energy conservation law, the volcanic radiation energy transfer equation under different irradiance conditions is established and solved jointly. In this paper, the study area is Halemaʻumaʻu crater in Hawaii, and the short-wave infrared band of Landsat 8 satellite day and night remote sensing images with an imaging interval of 36 hours are used as the study data, and the temperature and emissivity are calculated using the golden mean and parabolic interpolation method with the same emissivity of the same image element in both scenes and the temperature approximation as the constraints. The results are as follows: the temperature inversion of the study area has a banding phenomenon, the temperature of the lava lake is 800–1050 K and the emissivity is 0.5–0.7; the temperature of the crater surface outside the lava lake is 500–800 K and the emissivity is 0.7–1.0. The inversion results are consistent with the actual situation. The results show that the method can realize the simultaneous inversion of volcanic temperature and emissivity parameters on the image element scale, which provides a new method for the inversion of volcanic temperature and emissivity.

Sen2Like: Paving the Way towards Harmonization and Fusion of Optical Data

Satellite Earth Observation (EO) sensors are becoming a vital source of information for land surface monitoring. The concept of the Virtual Constellation (VC) is gaining interest within the science community owing to the increasing number of satellites/sensors in operation with similar characteristics. The establishment of a VC out of individual missions offers new possibilities for many application domains, in particular in the fields of land surface monitoring and change detection. In this context, this paper describes the Copernicus Sen2Like algorithms and software, a solution for harmonizing and fusing Landsat 8/Landsat 9 data with Sentinel-2 data. Developed under the European Union Copernicus Program, the Sen2Like software processes a large collection of Level 1/Level 2A products and generates high quality Level 2 Analysis Ready Data (ARD) as part of harmonized (Level 2H) and/or fused (Level 2F) products providing high temporal resolutions. For this purpose, we have re-used and developed a broad spectrum of data processing and analysis methodologies, including geometric and spectral co-registration, atmospheric and Bi-Directional Reflectance Distribution Function (BRDF) corrections and upscaling to 10 m for relevant Landsat bands. The Sen2Like software and the algorithms have been developed within a VC establishment framework, and the tool can conveniently be used to compare processing algorithms in combinations. It also has the potential to integrate new missions from spaceborne and airborne platforms including unmanned aerial vehicles. The validation activities show that the proposed approach improves the temporal consistency of the multi temporal data stack, and output products are interoperable with the subsequent thematic analysis processes.

Incorporation of Digital Elevation Model, Normalized Difference Vegetation Index, and Landsat-8 Data for Land Use Land Cover Mapping

Ancillary data are crucial in land use land cover (LULC) mapping process. This study goal is to investigate if adding Normalized Difference Vegetation Index (NDVI) and digital elevation model (DEM) data as ancillary data to the Landsat-8 spectral imagery (acquired on 14 April 2016) in the support vector machine (SVM ) classification process improves LULC mapping accuracy in GuaMusang, Malaysia. ENVI software was used to preprocess a single Landsat-8 image, convert it to reflectance, and calculate NDVI. ASTER-GDEM data were used to generate the DEM. The logical channel method was used to combine NDVI and DEM with Landsat-8 bands and limit the impact of shadows during SVM classification. The SVM accuracy was tested and evaluated on ancillary data and Landsat-8 spectral-based collection. The results revealed that the user's accuracy and producer's accuracy improved by 15.1% and 2.1%, for primary forest and by 17.93% and 28.86% for secondary forest, respectively. The classification reliability of the majority of LULC categories has increased significantly. Compared to SVM spectral-based set, the overall accuracy and kappa coefficient of the SVM ancillary-based set improved by 8.77% and 0.12, respectively. In conclusion, this article demonstrated that integrating DEM and NDVI data improves Landsat-8 image classification precision.

Land suitability assessment for second cropping in terms of low temperature stresses using landsat TIRS sensor

The second cropping which is done in the autumn after the main cultivation is one of the ways to increase food security, farmers' income, and thus prevent migration of villagers. The main limiting factor in autumn cultivation is the reduction in ambient and soil temperatures, which causes a severe drop in crop yield if it reaches below the physiological base temperature and freezing temperature. In Gilan, one of the northern provinces of Iran more than 90 % of agricultural land is cultivated once a year and has no production in half of the year. Accordingly, the purpose of the present study is to evaluate the feasibility of autumn cultivation of rice and hull-less seed pumpkin (Cucurbita pepo L. var. pepo subsp. styriaca) in terms low temperature stresses. In the first step, the land use map was prepared using the fusion of images with panchromatic band of Landsat 8 Maximum Likelihood classification method and then agricultural lands were separated. The land surface temperature (LST) maps were extracted on two dates, October 30, 2018 and December 17, 2019 using the TIRS sensor. Comparison of the estimated data with the meteorological data showed that LST was 0.6 °C higher than the meteorological data on October and it was 1.1 °C lower on December. Then, the LST map was validated with meteorological data in the last 10 years and a modified map was obtained to measure the cultivation potential of rice and hull-less seed pumpkin. Comparison of LST maps obtained on the two dates showed that the temperature variation was greater in the colder date. Considering base temperatures of 12 and 10 °C for rice and pumpkin, respectively, as well as the freezing temperature of 5 °C for these two crops, land suitability was identified. Having the minimum temperature of 15 °C for almost all lands, there will be no temperature stress for the crops until October 30. But, if the crop calendar lasts until December 17, only 2.62 % of agricultural lands have the potential to cultivate rice without temperature restrictions. Meanwhile, lands with cultivation potential for pumpkin were estimated 6983.3 ha (83.5 %) on December. Therefore, pumpkin cultivation has a lower temperature risk compared to rice in Rezvanshahr. The results of this study, in addition to being the required source for any planning in the field of autumn cultivation of rice and pumpkin, is one of the main sources for selecting different crops of the second cropping and their crop calendar.

Towards a combined Landsat-8 and Sentinel-2 for 10-m land surface temperature products: The Google Earth Engine monthly Ten-ST-GEE system

Efforts to combine satellite images from different sources are particularly needed in Land Surface Temperature-based (LST) studies. This research proposes for the first time, to our knowledge, a Google Earth Engine-based (GEE) 10-m LST system, named Ten-ST-GEE. It is based on both Landsat-8 and Sentinel-2 bands. Ten-ST-GEE has the ability to automatically transform 30-m to 10-m LST at Landsat-8 overpass time. Machine learning and regression methods (i.e., OLS, RLS, DisTrad, RF, and SVM) are embedded within this system. Ten-ST-GEE was applied over two agricultural lands and two urban regions in the United States of America and in Lebanon. OLS and RLS showed an RMSE of ∼1.1 °C compared to ∼2.4 °C for DisTrad and ∼2.5 °C for RF and SVM. The open-source and automated Ten-ST-GEE can generate information at the building-level and within the agricultural parcels. It has the potential to be portable to any region across the Globe, aiming at better management of environmental resources.

Inland Water Trophic State Identification using Remote Sensing data and Machine Learning Approach

Providing information on inland waters’ trophic state levels (oligotrophic, mesotrophic, eutrophic, and hypereutrophic) is considered more effective in communicating the lake’s conditions to the public and policymakers than water quality. It is highly demanding for a straightforward method to estimate inland waters’ trophic state. This study proposes a model for estimating the lake trophic state levels from remote sensing data. We used simulation data to overcome data limitations in building the classification model. The simulation data consists of one nanometer (nm) interval spectra, paired with calculated Secchi Disk Depth (SD in m) representing various water types. We convert the spectra into Landsat band configuration and classify SD into four trophic state levels. We compare four machine learning classification models, i.e., Classification and Regression Trees (CART), k-Nearest Neighbour (k-NN), Support Vector Machine (SVM), Random Forest (RF), and select the best model using the Kappa Index. We apply the selected model to satellite images and estimate trophic state levels of various lakes across time and space. Our result demonstrated that the developed model could robustly identify the lake trophic state levels. This rapid identification procedure could provide valuable spatial and temporal information of the lake’s conditions for the public and policymakers to support inland water sustainable management.

Sand Dunes Spectral Index Determination Using Machine Learning Model: Case study of Baiji Sand Dunes Field Northern Iraq

Monitoring the propagation of dunes is essential for natural hazard management. Accurate dunes mapping is critical in this situation. Landscape elements such as vegetation, water, dunes, and built-up are commonly separated using spectral indices. The discovery of dune features using a spectral index is one of the most significant achievements in earth observation. In this research, it was suggested Drifting Sand Index (DSI) is a newly created index that can be used to extract the land of dunes. The DSI is calculated using the normalized difference between six Landsat-8 bands (B, R, G, NIR, SWIR-1, SWIR-2). The linear SVM algorithm was implemented using library (LibLINEAR) in the R software to calculate a new linear equation. Two versions of the index have been proposed, the first is the complete version (DSI-C), and the second is the reduced version (DSI-R). The suggested indices results were compared to four previously proposed spectral indices (NDSI-1, NDSI-2, CI, and NDSLI). The acquired results demonstrated that the DSI-C and DSI-R had a high ability to distinguish between sand and different land covers, such as vegetation, water bodies, and various soil types. The average overall accuracy for all levels of the DSI-R, DSI-C, NDSI-1, NDSI-2, CI, and NDSLI was 88.59%, 83.43%, 78.030%, 68.52%, 65.98%, and 56.490%, respectively. The average Kappa Coefficient for DSI-R, DSI-C NDSI-1, NDSI-2, CI, and NDSLI was 77.20%, 66.87%, 56.076%, 37.073%, 31.978%, and 13.011%, respectively.

Novel Vision Transformer–Based Bi-LSTM Model for LU/LC Prediction—Javadi Hills, India

Continuous monitoring and observing of the earth’s environment has become interactive research in the field of remote sensing. Many researchers have provided the Land Use/Land Cover information for the past, present, and future for their study areas around the world. This research work builds the Novel Vision Transformer–based Bidirectional long-short term memory model for predicting the Land Use/Land Cover Changes by using the LISS-III and Landsat bands for the forest- and non-forest-covered regions of Javadi Hills, India. The proposed Vision Transformer model achieves a good classification accuracy, with an average of 98.76%. The impact of the Land Surface Temperature map and the Land Use/Land Cover classification map provides good validation results, with an average accuracy of 98.38%, during the process of bidirectional long short-term memory–based prediction analysis. The authors also introduced an application-based explanation of the predicted results through the Google Earth Engine platform of Google Cloud so that the predicted results will be more informative and trustworthy to the urban planners and forest department to take proper actions in the protection of the environment.

Can improving the spatial equity of urban green space mitigate the effect of urban heat islands? An empirical study

The role of urban green space (UGS) in mitigating the urban heat island (UHI) effect has been demonstrated in a growing body of literature. However, the potential influence of the spatial equity of UGS distribution on the UHI effect has largely been overlooked. The present study aims to identify this potential influence using the spatial equity of UGS and the land surface temperature (LST) as measures of UGS spatial distribution and UHIs, respectively. A comprehensive spatial distribution map of UGS was generated by combining the UGS coverage fraction data within urban impervious pixels and the green cover data outside urban impervious pixels. Then, the spatial equity of UGS distribution across all urban impervious pixels was determined using the Gini coefficient. In addition, an LST map was derived using the thermal infrared spectral bands of Landsat 8 OLI/TIRS products. A case study of Dongguan, a highly urbanized city in China, showed that (1) the distribution of both UGS and LSTs were spatially aggregated in all the towns of the city, (2) the LST of urban impervious pixels was negatively correlated with the area of surrounding UGS, and (3) the Gini coefficient of UGS was positively correlated with the proportion of hot and cool areas, but negatively correlated with the proportion of medium-hot and medium-cool areas. These findings indicate that increasing the amount of UGS is beneficial to the reduction of urban average LSTs, while promoting the spatial equity of UGS distribution is conducive to reducing the spatial aggregation of LSTs within urban areas, thereby improving the overall urban thermal environment. Therefore, as a nature-based solution, promoting the spatial equity of UGS distribution could enhance the overall cooling effect of UGS more effectively at the city scale, and thus further underpin the sustainable development of the urban environment.

Urban Land Use and Land Cover Change Analysis Using Random Forest Classification of Landsat Time Series

Efficient implementation of remote sensing image classification can facilitate the extraction of spatiotemporal information for land use and land cover (LULC) classification. Mapping LULC change can pave the way to investigate the impacts of different socioeconomic and environmental factors on the Earth’s surface. This study presents an algorithm that uses Landsat time-series data to analyze LULC change. We applied the Random Forest (RF) classifier, a robust classification method, in the Google Earth Engine (GEE) using imagery from Landsat 5, 7, and 8 as inputs for the 1985 to 2019 period. We also explored the performance of the pan-sharpening algorithm on Landsat bands besides the impact of different image compositions to produce a high-quality LULC map. We used a statistical pan-sharpening algorithm to increase multispectral Landsat bands’ (Landsat 7–9) spatial resolution from 30 m to 15 m. In addition, we checked the impact of different image compositions based on several spectral indices and other auxiliary data such as digital elevation model (DEM) and land surface temperature (LST) on final classification accuracy based on several spectral indices and other auxiliary data on final classification accuracy. We compared the classification result of our proposed method and the Copernicus Global Land Cover Layers (CGLCL) map to verify the algorithm. The results show that: (1) Using pan-sharpened top-of-atmosphere (TOA) Landsat products can produce more accurate results for classification instead of using surface reflectance (SR) alone; (2) LST and DEM are essential features in classification, and using them can increase final accuracy; (3) the proposed algorithm produced higher accuracy (94.438% overall accuracy (OA), 0.93 for Kappa, and 0.93 for F1-score) than CGLCL map (84.4% OA, 0.79 for Kappa, and 0.50 for F1-score) in 2019; (4) the total agreement between the classification results and the test data exceeds 90% (93.37–97.6%), 0.9 (0.91–0.96), and 0.85 (0.86–0.95) for OA, Kappa values, and F1-score, respectively, which is acceptable in both overall and Kappa accuracy. Moreover, we provide a code repository that allows classifying Landsat 4, 5, 7, and 8 within GEE. This method can be quickly and easily applied to other regions of interest for LULC mapping.

Assessing Image Classification Accuracy with Principal Component Analysis Algorithm Case Study: Odeda LGA of Ogun State, Southwest Nigeria

The aim of this study is to assess image classification accuracy using the instrumentality of Principal Component Analysis (PCA). It is focused on evaluating the accruable benefits of Principal Component Analysis as part of an image preprocessing procedure for image classification. Land use land cover (LULC) and accuracy assessment datasets were obtained with remote sensing and geographic information system’s software. The principal component analysis was statistically used to assess the level of correlation amongst bands in Landsat 8. The image classification was premised on the Maximum Likelihood classifier for land use land cover analysis. To ascertain the accuracy of the classified images, the Producer’s accuracy, User’s accuracy and Kappa coefficient derivatives of accuracy assessment was calculated. The results revealed that the first three PCs of the raw Landsat data accounted for 99.37 % variance of the original Landsat data, while the last three PCs represented only 0.63% of the original data. The results of land use land cover based on raw bands composite were Forest (41%), Shrubs (33%) and Built-up (26%) respectively. On the other hand, land use land cover based on Principal Component Analysis showed Forest (39%), Shrubs (39%) and Built-up (22%) respectively. Comparing the results of Kappa coefficients of both LULC of raw bands’ composite was 0.88 while that of PCA was 0.91. Conclusively, there is a significant level of difference in the classification outputs of PCA derived classification and that of raw Landsat bands’ composite.

PLASTIC COVER GREENHOUSES REFLECTANCE SPECTRA FROM DIFFERENT OPTICAL SATELLITE IMAGERY

Abstract. Mapping the distribution of plastic covered greenhouses (PCG) is essential for any attempts to manage these complex areas of intensive agriculture. It is therefore important to understand how the spectrum of different PCG varies in order to establish its unique absorption features and how these can be utilised for mapping PCG from remote sensing imagery. This paper presents an analysis of the surface reflectance values of satellite image spectra for 50 PCG. The reflectance of these PCG, located in Almería (Spain), was studied in two seasons of the year (summer and winter). All single bands of WorldView-3 (WV3), Sentinel-2 MSI (S2 L2A) and Landsat 8 OLI (L8 L2), together with Normalized Difference Plastic Index (NDPI) and Normalized Difference Vegetation Index (NDVI), were generated through an object-based image analysis (OBIA) approach for each PCG and season. The results showed the variability of absorption features and overall shape of the spectra for all PCG. The main differences in reflectance were attributed to the crops and the specific characteristics of their local management. A relationship between brightness and whitewashing (greenhouse roof painted with lime to provide shade and reduce the temperature inside the greenhouse, especially in summer) was found, showing the ability of whitewashing to temporally mask the spectral signature of the plastic film.