Remote Sensing-Based Mapping of Senescent Leaf C:N Ratio in the Sundarbans Reserved Forest Using Machine Learning Techniques

Carbon to nitrogen ratio (C:N) of senescent leaf is a crucial functional trait and indicator of litter quality that affects belowground carbon and nitrogen cycles, especially soil decomposition. Although mapping the C:N ratio of fresh mature canopies has been attempted, few studies have attempted to map the C:N ratio of senescent leaves, particularly in mangroves. In this study, four machine learning models (Stochastic Gradient Boosting, SGB; Random Forest, RF; Support Vector Machine, SVM; and Partial Least Square Regression, PLSR) were compared for testing the predictability of using the Landsat TM 5 (LTM5) and Landsat 8 to map spatial and temporal distribution of C:N ratio of senescent leaves in Sundarbans Reserved Forest (SRF), Bangladesh. Surface reflectance of bands, texture metrics of bands and vegetation indices of LTM5 and Landsat 8 yearly composite images were extracted using Google Earth Engine for 2009–2010 and 2019. We found SGB, RF and SVM were significant different from PLSR based on MAE, RMSE, and R2 (p < 0.05). Our results indicate that remote sensing data, such as Landsat TM data, can be used to map the C:N ratio of senescent leaves in mangroves with reasonable accuracy. We also found that the mangroves had a high spatial variation of C:N ratio and the C:N ratio map developed in the current study can be used for improving the biogeochemical and ecosystem models in the mangroves.

Download Full-text

Monitoring the Foliar Nutrients Status of Mango Using Spectroscopy-Based Spectral Indices and PLSR-Combined Machine Learning Models

Remote Sensing ◽

10.3390/rs13040641 ◽

2021 ◽

Vol 13 (4) ◽

pp. 641

Author(s):

Gopal Ramdas Mahajan ◽

Bappa Das ◽

Dayesh Murgaokar ◽

Ittai Herrmann ◽

Katja Berger ◽

...

Keyword(s):

Machine Learning ◽

Remote Sensing ◽

Partial Least Square ◽

Least Square ◽

Partial Least Square Regression ◽

Support Vector ◽

Spectral Indices ◽

Learning Models ◽

Leaf Nutrients ◽

Machine Learning Models

Conventional methods of plant nutrient estimation for nutrient management need a huge number of leaf or tissue samples and extensive chemical analysis, which is time-consuming and expensive. Remote sensing is a viable tool to estimate the plant’s nutritional status to determine the appropriate amounts of fertilizer inputs. The aim of the study was to use remote sensing to characterize the foliar nutrient status of mango through the development of spectral indices, multivariate analysis, chemometrics, and machine learning modeling of the spectral data. A spectral database within the 350–1050 nm wavelength range of the leaf samples and leaf nutrients were analyzed for the development of spectral indices and multivariate model development. The normalized difference and ratio spectral indices and multivariate models–partial least square regression (PLSR), principal component regression, and support vector regression (SVR) were ineffective in predicting any of the leaf nutrients. An approach of using PLSR-combined machine learning models was found to be the best to predict most of the nutrients. Based on the independent validation performance and summed ranks, the best performing models were cubist (R2 ≥ 0.91, the ratio of performance to deviation (RPD) ≥ 3.3, and the ratio of performance to interquartile distance (RPIQ) ≥ 3.71) for nitrogen, phosphorus, potassium, and zinc, SVR (R2 ≥ 0.88, RPD ≥ 2.73, RPIQ ≥ 3.31) for calcium, iron, copper, boron, and elastic net (R2 ≥ 0.95, RPD ≥ 4.47, RPIQ ≥ 6.11) for magnesium and sulfur. The results of the study revealed the potential of using hyperspectral remote sensing data for non-destructive estimation of mango leaf macro- and micro-nutrients. The developed approach is suggested to be employed within operational retrieval workflows for precision management of mango orchard nutrients.

Download Full-text

Object-Oriented LULC Classification in Google Earth Engine Combining SNIC, GLCM, and Machine Learning Algorithms

Remote Sensing ◽

10.3390/rs12223776 ◽

2020 ◽

Vol 12 (22) ◽

pp. 3776

Author(s):

Andrea Tassi ◽

Marco Vizzari

Keyword(s):

Machine Learning ◽

Central Italy ◽

Object Oriented ◽

Google Earth ◽

Machine Learning Algorithms ◽

Support Vector ◽

Landsat 8 ◽

Good Reliability ◽

Google Earth Engine ◽

Occurrence Matrix

Google Earth Engine (GEE) is a versatile cloud platform in which pixel-based (PB) and object-oriented (OO) Land Use–Land Cover (LULC) classification approaches can be implemented, thanks to the availability of the many state-of-art functions comprising various Machine Learning (ML) algorithms. OO approaches, including both object segmentation and object textural analysis, are still not common in the GEE environment, probably due to the difficulties existing in concatenating the proper functions, and in tuning the various parameters to overcome the GEE computational limits. In this context, this work is aimed at developing and testing an OO classification approach combining the Simple Non-Iterative Clustering (SNIC) algorithm to identify spatial clusters, the Gray-Level Co-occurrence Matrix (GLCM) to calculate cluster textural indices, and two ML algorithms (Random Forest (RF) or Support Vector Machine (SVM)) to perform the final classification. A Principal Components Analysis (PCA) is applied to the main seven GLCM indices to synthesize in one band the textural information used for the OO classification. The proposed approach is implemented in a user-friendly, freely available GEE code useful to perform the OO classification, tuning various parameters (e.g., choose the input bands, select the classification algorithm, test various segmentation scales) and compare it with a PB approach. The accuracy of OO and PB classifications can be assessed both visually and through two confusion matrices that can be used to calculate the relevant statistics (producer’s, user’s, overall accuracy (OA)). The proposed methodology was broadly tested in a 154 km2 study area, located in the Lake Trasimeno area (central Italy), using Landsat 8 (L8), Sentinel 2 (S2), and PlanetScope (PS) data. The area was selected considering its complex LULC mosaic mainly composed of artificial surfaces, annual and permanent crops, small lakes, and wooded areas. In the study area, the various tests produced interesting results on the different datasets (OA: PB RF (L8 = 72.7%, S2 = 82%, PS = 74.2), PB SVM (L8 = 79.1%, S2 = 80.2%, PS = 74.8%), OO RF (L8 = 64%, S2 = 89.3%, PS = 77.9), OO SVM (L8 = 70.4, S2 = 86.9%, PS = 73.9)). The broad code application demonstrated very good reliability of the whole process, even though the OO classification process resulted, sometimes, too demanding on higher resolution data, considering the available computational GEE resources.

Download Full-text

Comparative Analysis of Machine Learning Algorithms in Automatic Identification and Extraction of Water Boundaries

Applied Sciences ◽

10.3390/app112110062 ◽

2021 ◽

Vol 11 (21) ◽

pp. 10062

Author(s):

Aimin Li ◽

Meng Fan ◽

Guangduo Qin ◽

Youcheng Xu ◽

Hailong Wang

Keyword(s):

Machine Learning ◽

Remote Sensing ◽

Decision Tree ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Water Bodies ◽

Support Vector ◽

Landsat 8 ◽

Transfer Performance ◽

Remote Sensing Images

Monitoring open water bodies accurately is important for assessing the role of ecosystem services in the context of human survival and climate change. There are many methods available for water body extraction based on remote sensing images, such as the normalized difference water index (NDWI), modified NDWI (MNDWI), and machine learning algorithms. Based on Landsat-8 remote sensing images, this study focuses on the effects of six machine learning algorithms and three threshold methods used to extract water bodies, evaluates the transfer performance of models applied to remote sensing images in different periods, and compares the differences among these models. The results are as follows. (1) Various algorithms require different numbers of samples to reach their optimal consequence. The logistic regression algorithm requires a minimum of 110 samples. As the number of samples increases, the order of the optimal model is support vector machine, neural network, random forest, decision tree, and XGBoost. (2) The accuracy evaluation performance of each machine learning on the test set cannot represent the local area performance. (3) When these models are directly applied to remote sensing images in different periods, the AUC indicators of each machine learning algorithm for three regions all show a significant decline, with a decrease range of 0.33–66.52%, and the differences among the different algorithm performances in the three areas are obvious. Generally, the decision tree algorithm has good transfer performance among the machine learning algorithms with area under curve (AUC) indexes of 0.790, 0.518, and 0.697 in the three areas, respectively, and the average value is 0.668. The Otsu threshold algorithm is the optimal among threshold methods, with AUC indexes of 0.970, 0.617, and 0.908 in the three regions respectively and an average AUC of 0.832.

Download Full-text

Machine learning-based ship detection and tracking using satellite images for maritime surveillance

Journal of Ambient Intelligence and Smart Environments ◽

10.3233/ais-210610 ◽

2021 ◽

Vol 13 (5) ◽

pp. 361-371

Author(s):

Yu Wang ◽

G. Rajesh ◽

X. Mercilin Raajini ◽

N. Kritika ◽

A. Kavinkumar ◽

...

Keyword(s):

Machine Learning ◽

Remote Sensing ◽

Satellite Images ◽

Google Earth ◽

Support Vector ◽

Linear Discriminant ◽

Ship Detection ◽

Maritime Surveillance ◽

Detection And Tracking ◽

Multiple Hypothesis Tracking

The recent advancement in remote sensing technologies has resulted in the availability of different imaging modes and higher resolution satellite images. Accessibility of these remote sensing or satellite images, automatic ship detection and tracking has become an important research topic in the field of maritime surveillance. In this paper, a novel method for ship detection using satellite images is proposed. First the preprocessing is carried out to remove the noise from the images using Ship Detection and Tracking (SDT) filter. Then, the land masking (sea-land area separation) and cloud masking is carried out based on the gradient feature extraction using SDT edge detection, along with SDT segmentation. Finally, the ships are identified using the Machine Learning (ML) classifiers like Support Vector Machine (SVM), Random Forest Classifier (RFC), Linear Discriminant Analysis (LDA), Logistic Regression (LR), KNN, and Gaussian Naïve Bayes-based classifier based on the features extracted from Histogram of Oriented Gradients (HOG). The proposed work is cross validated using the Google earth data. Performance of our proposed method is evaluated using the recall and the precision values. Further, for tracking ships, an improved multiple hypothesis tracking (MHT) algorithm is proposed and tested using the Kaggle dataset.

Download Full-text

Combining Radar and Optical Satellite Imagery with Machine Learning to Map Lava Flows at Mount Etna and Fogo Island

Energies ◽

10.3390/en14010197 ◽

2021 ◽

Vol 14 (1) ◽

pp. 197

Author(s):

Claudia Corradino ◽

Giuseppe Bilotta ◽

Annalisa Cappello ◽

Luigi Fortuna ◽

Ciro Del Negro

Keyword(s):

Machine Learning ◽

Change Detection ◽

Lava Flow ◽

Satellite Data ◽

Google Earth ◽

Lava Flows ◽

Mount Etna ◽

Support Vector ◽

Landsat 8 ◽

Flow Mapping

Lava flow mapping has direct relevance to volcanic hazards once an eruption has begun. Satellite remote sensing techniques are increasingly used to map newly erupted lava, thanks to their capability to survey large areas with frequent revisit time and accurate spatial resolution. Visible and infrared satellite data are routinely used to detect the distributions of volcanic deposits and monitor thermal features, even if clouds are a serious obstacle for optical sensors, since they cannot be penetrated by optical radiation. On the other hand, radar satellite data have been playing an important role in surface change detection and image classification, being able to operate in all weather conditions, although their use is hampered by the special imaging geometry, the complicated scattering process, and the presence of speckle noise. Thus, optical and radar data are complementary data sources that can be used to map lava flows effectively, in addition to alleviating cloud obstruction and improving change detection performance. Here, we propose a machine learning approach based on the Google Earth Engine (GEE) platform to analyze simultaneously the images acquired by the synthetic aperture radar (SAR) sensor, on board of Sentinel-1 mission, and by optical and multispectral sensors of Landsat-8 missions and Multi-Spectral Imager (MSI), on board of Sentinel-2 mission. Machine learning classifiers, including K-means algorithm (K-means) and support vector machine (SVM), are used to map lava flows automatically from a combination of optical and SAR images. We describe the operation of this approach by using a retrospective analysis of two recent lava flow-forming eruptions at Mount Etna (Italy) and Fogo Island (Cape Verde). We found that combining both radar and optical imagery improved the accuracy and reliability of lava flow mapping. The results highlight the need to fully exploit the extraordinary potential of complementary satellite sensors to provide time-critical hazard information during volcanic eruptions.

Download Full-text

Coral Reef Mapping with Remote Sensing and Machine Learning: A Nurture and Nature Analysis in Marine Protected Areas

Remote Sensing ◽

10.3390/rs13152907 ◽

2021 ◽

Vol 13 (15) ◽

pp. 2907

Author(s):

Camila Brasil Louro da Silveira ◽

Gil Marcelo Reuss Strenzel ◽

Mauro Maida ◽

Ana Lídia Bertoldi Gaspar ◽

Beatrice Padovani Ferreira

Keyword(s):

Machine Learning ◽

Remote Sensing ◽

Coral Reefs ◽

Protected Areas ◽

Marine Protected Areas ◽

Distribution Model ◽

Support Vector ◽

Landsat 8 ◽

Human Use ◽

The Impact

Mapping habitats is essential to assist strategic decisions regarding the use and protection of coral reefs. Coupled with machine learning (ML) algorithms, remote sensing has allowed detailed mapping of reefs at meaningful scales. Here we integrated WorldView-3 and Landsat-8 imagery and ML techniques to produce a map of suitable habitats for the occurrence of a model species, the hydrocoral Millepora alcicornis, in coral reefs located inside marine protected areas in Northeast Brazil. Conservation and management efforts in the region were also analyzed, integrating human use layers to the ecological seascape. Three ML techniques were applied: two to derive base layers, namely geographically weighted regressions for bathymetry and support vector machine classifier (SVM) for habitat mapping, and one to build the species distribution model (MaxEnt) for Millepora alcicornis, a conspicuous and important reef-building species in the area. Additionally, human use was mapped based on the presence of tourists and fishers. SVM yielded 15 benthic classes (e.g., seagrass, sand, coral), with an overall accuracy of 79%. Bathymetry and its derivative layers depicted the topographical complexity of the area. The Millepora alcicornis distribution model identified distance from the shore and depth as topographical factors limiting the settling and growth of coral colonies. The most important variables were ecological, showing the importance of maintaining high biodiversity in the ecosystem. The comparison of the habitat suitability model with species absence and human use maps indicated the impact of direct human activities as potential inhibitors of coral development. Results reinforce the importance of the establishment of no-take zones and other protective measures for maintaining local biodiversity.

Download Full-text

PIXEL BASED LANDSLIDE IDENTIFICATION USING LANDSAT 8 AND GEE

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xliii-b3-2021-721-2021 ◽

2021 ◽

Vol XLIII-B3-2021 ◽

pp. 721-726

Author(s):

P. Singh ◽

V. Maurya ◽

R. Dwivedi

Keyword(s):

Machine Learning ◽

Research Work ◽

Volcanic Eruptions ◽

Google Earth ◽

Machine Learning Algorithms ◽

Supervised Machine Learning ◽

Geological Survey ◽

Support Vector ◽

Landsat 8 ◽

Multi Band

Abstract. Landslide is one of the most common natural disasters triggered mainly due to heavy rainfall, cloud burst, earthquake, volcanic eruptions, unorganized constructions of roads, and deforestation. In India, field surveying is the most common method used to identify potential landslide regions and update the landslide inventories maintained by the Geological Survey of India, but it is very time-consuming, costly, and inefficient. Alternatively, advanced remote sensing technologies in landslide analysis allow rapid and easy data acquisitions and help to improve the traditional method of landslide detection capabilities. Supervised Machine learning algorithms, for example, Support Vector Machine (SVM), are challenging to conventional techniques by predicting disasters with astounding accuracy. In this research work, we have utilized open-source datasets (Landsat 8 multi-band images and JAXA ALOS DSM) and Google Earth Engine (GEE) to identify landslides in Rudraprayag using machine learning techniques. Rudraprayag is a district of Uttarakhand state in India, which has always been the center of attention of geological studies due to its higher density of landslide-prone zones. For the training and validation purpose, labeled landslide locations obtained from landslide inventory (prepared by the Geological Survey of India) and layers such as NDVI, NDWI, and slope (generated from JAXA ALOS DSM and Landsat 8 satellite multi-band imagery) were used. The landslide identification has been performed using SVM, Classification and Regression Trees (CART), Minimum Distance, Random forest (RF), and Naïve Bayes techniques, in which SVM and RF outperformed all other techniques by achieving an 87.5% true positive rate (TPR).

Download Full-text

Assessing the Effect of Training Sampling Design on the Performance of Machine Learning Classifiers for Land Cover Mapping Using Multi-Temporal Remote Sensing Data and Google Earth Engine

Remote Sensing ◽

10.3390/rs13081433 ◽

2021 ◽

Vol 13 (8) ◽

pp. 1433

Author(s):

Shobitha Shetty ◽

Prasun Kumar Gupta ◽

Mariana Belgiu ◽

S. K. Srivastav

Keyword(s):

Machine Learning ◽

Remote Sensing ◽

Random Sampling ◽

Sampling Design ◽

Remote Sensing Data ◽

Google Earth ◽

Machine Learning Classifiers ◽

Learning Classifiers ◽

Multi Temporal ◽

Google Earth Engine

Machine learning classifiers are being increasingly used nowadays for Land Use and Land Cover (LULC) mapping from remote sensing images. However, arriving at the right choice of classifier requires understanding the main factors influencing their performance. The present study investigated firstly the effect of training sampling design on the classification results obtained by Random Forest (RF) classifier and, secondly, it compared its performance with other machine learning classifiers for LULC mapping using multi-temporal satellite remote sensing data and the Google Earth Engine (GEE) platform. We evaluated the impact of three sampling methods, namely Stratified Equal Random Sampling (SRS(Eq)), Stratified Proportional Random Sampling (SRS(Prop)), and Stratified Systematic Sampling (SSS) upon the classification results obtained by the RF trained LULC model. Our results showed that the SRS(Prop) method favors major classes while achieving good overall accuracy. The SRS(Eq) method provides good class-level accuracies, even for minority classes, whereas the SSS method performs well for areas with large intra-class variability. Toward evaluating the performance of machine learning classifiers, RF outperformed Classification and Regression Trees (CART), Support Vector Machine (SVM), and Relevance Vector Machine (RVM) with a >95% confidence level. The performance of CART and SVM classifiers were found to be similar. RVM achieved good classification results with a limited number of training samples.

Download Full-text

Machine Learning Comparison and Parameter Setting Methods for the Detection of Dump Sites for Construction and Demolition Waste Using the Google Earth Engine

Remote Sensing ◽

10.3390/rs13040787 ◽

2021 ◽

Vol 13 (4) ◽

pp. 787

Author(s):

Lei Zhou ◽

Ting Luo ◽

Mingyi Du ◽

Qiang Chen ◽

Yang Liu ◽

...

Keyword(s):

Machine Learning ◽

Remote Sensing ◽

Google Earth ◽

Construction And Demolition Waste ◽

Parameterization Scheme ◽

Classification Methods ◽

Demolition Waste ◽

Optimal Method ◽

Identification Method ◽

Google Earth Engine

Machine learning has been successfully used for object recognition within images. Due to the complexity of the spectrum and texture of construction and demolition waste (C&DW), it is difficult to construct an automatic identification method for C&DW based on machine learning and remote sensing data sources. Machine learning includes many types of algorithms; however, different algorithms and parameters have different identification effects on C&DW. Exploring the optimal method for automatic remote sensing identification of C&DW is an important approach for the intelligent supervision of C&DW. This study investigates the megacity of Beijing, which is facing high risk of C&DW pollution. To improve the classification accuracy of C&DW, buildings, vegetation, water, and crops were selected as comparative training samples based on the Google Earth Engine (GEE), and Sentinel-2 was used as the data source. Three classification methods of typical machine learning algorithms (classification and regression trees (CART), random forest (RF), and support vector machine (SVM)) were selected to classify the C&DW from remote sensing images. Using empirical methods, the experimental trial method, and the grid search method, the optimal parameterization scheme of the three classification methods was studied to determine the optimal method of remote sensing identification of C&DW based on machine learning. Through accuracy evaluation and ground verification, the overall recognition accuracies of CART, RF, and SVM for C&DW were 73.12%, 98.05%, and 85.62%, respectively, under the optimal parameterization scheme determined in this study. Among these algorithms, RF was a better C&DW identification method than were CART and SVM when the number of decision trees was 50. This study explores the robust machine learning method for automatic remote sensing identification of C&DW and provides a scientific basis for intelligent supervision and resource utilization of C&DW.

Download Full-text

Mapping Allochemical Limestone Formations in Hazara, Pakistan Using Google Cloud Architecture: Application of Machine-Learning Algorithms on Multispectral Data

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi10020058 ◽

2021 ◽

Vol 10 (2) ◽

pp. 58

Author(s):

Muhammad Fawad Akbar Khan ◽

Khan Muhammad ◽

Shahid Bashir ◽

Shahab Ud Din ◽

Muhammad Hanif

Keyword(s):

Machine Learning ◽

Remote Sensing ◽

Learning Algorithms ◽

Remote Sensing Data ◽

Kappa Coefficient ◽

Machine Learning Algorithms ◽

Landsat 8 ◽

Sensing Data ◽

Fossiliferous Limestone

Low-resolution Geological Survey of Pakistan (GSP) maps surrounding the region of interest show oolitic and fossiliferous limestone occurrences correspondingly in Samanasuk, Lockhart, and Margalla hill formations in the Hazara division, Pakistan. Machine-learning algorithms (MLAs) have been rarely applied to multispectral remote sensing data for differentiating between limestone formations formed due to different depositional environments, such as oolitic or fossiliferous. Unlike the previous studies that mostly report lithological classification of rock types having different chemical compositions by the MLAs, this paper aimed to investigate MLAs’ potential for mapping subclasses within the same lithology, i.e., limestone. Additionally, selecting appropriate data labels, training algorithms, hyperparameters, and remote sensing data sources were also investigated while applying these MLAs. In this paper, first, oolitic (Samanasuk), fossiliferous (Lockhart and Margalla) limestone-bearing formations along with the adjoining Hazara formation were mapped using random forest (RF), support vector machine (SVM), classification and regression tree (CART), and naïve Bayes (NB) MLAs. The RF algorithm reported the best accuracy of 83.28% and a Kappa coefficient of 0.78. To further improve the targeted allochemical limestone formation map, annotation labels were generated by the fusion of maps obtained from principal component analysis (PCA), decorrelation stretching (DS), X-means clustering applied to ASTER-L1T, Landsat-8, and Sentinel-2 datasets. These labels were used to train and validate SVM, CART, NB, and RF MLAs to obtain a binary classification map of limestone occurrences in the Hazara division, Pakistan using the Google Earth Engine (GEE) platform. The classification of Landsat-8 data by CART reported 99.63% accuracy, with a Kappa coefficient of 0.99, and was in good agreement with the field validation. This binary limestone map was further classified into oolitic (Samanasuk) and fossiliferous (Lockhart and Margalla) formations by all the four MLAs; in this case, RF surpassed all the other algorithms with an improved accuracy of 96.36%. This improvement can be attributed to better annotation, resulting in a binary limestone classification map, which formed a mask for improved classification of oolitic and fossiliferous limestone in the area.

Download Full-text