Riverscape classification by using machine learning in combination with satellite and UAV images

2020 ◽  
Author(s):  
Hitoshi Miyamoto ◽  
Takuya Sato ◽  
Akito Momose ◽  
Shuji Iwami
Keyword(s):  
Machine Learning ◽  
Satellite Images ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Training Data ◽  
Low Resolution ◽  
Critical Areas ◽  
Aerial Vehicle ◽  
Uav Images

<p>This presentation examined a new method for classifying riverine land covers by using the machine learning technique applied to both the satellite and UAV (Unmanned Aerial Vehicle) images in a Kurobe River channel.  The method used Random Forests (RF) for the classification with RGBs and NDVIs (Normalized Difference Vegetation Index) of the images in combination.  In the process, the high-resolution UAV images made it possible to create accurate training data for the land cover classification of the low-resolution satellite images.  The results indicated that the combination of the high- and low-resolution images in the machine learning could effectively detect waters, gravel/sand beds, trees, and grasses from the satellite images with a certain degree of accuracy.  In contrast, the usage of only low-resolution satellite images failed to detect the vegetation difference between trees and grasses.  These results could actively support the effectiveness of the present machine learning method in the combination of satellite and UAV images to grasp the most critical areas in riparian vegetation management.</p>

scholarly journals Using UAV Multispectral Images for Classification of Forest Burn Severity—A Case Study of the 2019 Gangneung Forest Fire

Forests ◽  
2019 ◽  
Vol 10 (11) ◽  
pp. 1025 ◽  
Author(s):  
Jung-il Shin ◽  
Won-woo Seo ◽  
Taejung Kim ◽  
Joowon Park ◽  
Choong-shik Woo
Keyword(s):  
Forest Fire ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Accurate Method ◽  
Burn Severity ◽  
Spectral Angle Mapper ◽  
Before And After ◽  
Uav Images ◽  
Uav Image

Unmanned aerial vehicle (UAV)-based remote sensing has limitations in acquiring images before a forest fire, although burn severity can be analyzed by comparing images before and after a fire. Determining the burned surface area is a challenging class in the analysis of burn area severity because it looks unburned in images from aircraft or satellites. This study analyzes the availability of multispectral UAV images that can be used to classify burn severity, including the burned surface class. RedEdge multispectral UAV image was acquired after a forest fire, which was then processed into a mosaic reflectance image. Hundreds of samples were collected for each burn severity class, and they were used as training and validation samples for classification. Maximum likelihood (MLH), spectral angle mapper (SAM), and thresholding of a normalized difference vegetation index (NDVI) were used as classifiers. In the results, all classifiers showed high overall accuracy. The classifiers also showed high accuracy for classification of the burned surface, even though there was some confusion among spectrally similar classes, unburned pine, and unburned deciduous. Therefore, multispectral UAV images can be used to analyze burn severity after a forest fire. Additionally, NDVI thresholding can also be an easy and accurate method, although thresholds should be generalized in the future.

scholarly journals Mapeamento e Quantificação da Cobertura Vegetal no Agreste Central de Pernambuco Utilizando Técnicas de Empilhamento e o NDVI (Mapping and Quantification of Vegetation Cover from Central Agreste Region of Pernambuco State Using NDVI Technique)

2011 ◽  
Vol 3 (3) ◽  
pp. 157
Author(s):  
Daniel Rodrigues Lira ◽  
Maria do Socorro Bezerra de Araújo ◽  
Everardo Valadares De Sá Barretto Sampaio ◽  
Hewerton Alves da Silva
Keyword(s):  
Remote Sensing ◽  
Vegetation Cover ◽  
Satellite Images ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Regional Scale ◽  
Digital Processing ◽  
Sparse Vegetation ◽  
New Sensors

O mapeamento e monitoramento da cobertura vegetal receberam consideráveis impulsos nas últimas décadas, com o advento do sensoriamento remoto, processamento digital de imagens e políticas de combate ao desmatamento, além dos avanços nas pesquisas e gerações de novos sensores orbitais e sua distribuição de forma mais acessível aos usuários, tornam as imagens de satélite um dos produtos do sensoriamento remoto mais utilizado para análises da cobertura vegetal das terras. Os índices de cobertura vegetal deste trabalho foram obtidos usando o NDVI - Normalized Difference Vegetation Index para o Agreste central de Pernambuco indicou 39,7% de vegetação densa, 13,6% de vegetação esparsa, 14,3% de vegetação rala e 10,5% de solo exposto. O NDVI apresentou uma caracterização satisfatória para a classificação do estado da vegetação do ano de 2007 para o Agreste Central pernambucano, porém ocorreu uma confusão com os índices de nuvens, sombras e solos exposto, necessitando de uma adaptação na técnica para um melhor aprimoramento da diferenciação desses elementos, constituindo numa recombinação de bandas após a elaboração e calculo do NDVI.Palavras-chave: Geoprocessamento; sensoriamento remoto; índice de vegetação. Mapping and Quantification of Vegetation Cover from Central Agreste Region of Pernambuco State Using NDVI Technique ABSTRACTIn recent decades, advanced techniques for mapping and monitoring vegetation cover have been developed with the advent of remote sensing. New tools for digital processing, the generation of new sensors and their orbital distribution more accessible have facilitated the acquisition and use of satellite images, making them one of the products of remote sensing more used for analysis of the vegetation cover. The aim of this study was to assess the vegetation cover from Central Agreste region of Pernambuco State, using satellite images TM / LANDSAT-5. The images were processed using the NDVI (Normalized Difference Vegetation Index) technique, generating indexes used for classification of vegetation in dense, sparse and scattered. There was a proportion of 39.7% of dense vegetation, 13.6% of sparse vegetation, 14.3% of scattered vegetation and 10.5% of exposed soil. NDVI technique has been used as a useful tool in the classification of vegetation on a regional scale, however, needs improvement to a more precise differentiation among levels of clouds, shadow, exposed soils and vegetation. Keywords: Geoprocessing, remote sensing, vegetation index

scholarly journals Using unmanned aerial vehicle for identifying the vegetative vigor and quantify the area occupied by eucalyptus sprouts after chemical weeding in the state of Bahia, Brazil

2020 ◽  
pp. 165
Author(s):  
Caique Carvalho Medauar ◽  
Samuel de Assis Silva ◽  
Luis Carlos Cirilo Carvalho ◽  
Rafael Augusto Soares Tibúrcio ◽  
Paullo Augusto Silva Medauar
Keyword(s):  
Unmanned Aerial Vehicle ◽  
Supervised Classification ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
New Technologies ◽  
Sampling Methods ◽  
Control Method ◽  
Aerial Images ◽  
Aerial Vehicle

Currently, the efficiency of chemical weeding for controlling eucalyptus sprouts is measured by field sampling, but the inefficiency of the sampling methods has led to the investigation of new technologies, such as using unmanned aerial vehicle (UAV) to help to identify the vegetative vigor of eucalyptus after chemical weeding. This study, therefore, used aerial images obtained by a UAV embedded with a sensor to identify the vegetative vigor and quantify the area occupied by eucalyptus sprouts 90 days after the chemical weeding. The study was conducted in three fields planted with eucalyptus whose sprouts had been previously controlled by the chemical weeding with the Scout® herbicide in November 2016. The vegetative vigor of the eucalyptus sprouts was evaluated from the aerial images obtained by the UAV with embedded sensor, during flights conducted in November 2016 and February 2017, that were used to calculate the normalized difference vegetation index and later, a random sample grid was constructed for each image by supervised classification of the area (m2) to determine the percentage occupied by the sprouts. The used chemical control method neither eradicated the sprouts nor reduced the sprout occupied area. The normalized difference vegetation index and supervised classification tools allowed determining with high precision sprout health status and size, generating interpretable data on the different evaluated fields and periods. The processing of the images obtained by the UAV provided a viable alternative of management to evaluate sprout status in reforestation areas.

scholarly journals Classification of Soybean Pubescence from Multispectral Aerial Imagery

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Robert W. Bruce ◽  
Istvan Rajcan ◽  
John Sulik
Keyword(s):  
Plant Breeding ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Accurate Determination ◽  
Principal Component ◽  
Training Data ◽  
Aerial Imagery ◽  
Aerial Images ◽  
Support Vector

The accurate determination of soybean pubescence is essential for plant breeding programs and cultivar registration. Currently, soybean pubescence is classified visually, which is a labor-intensive and time-consuming activity. Additionally, the three classes of phenotypes (tawny, light tawny, and gray) may be difficult to visually distinguish, especially the light tawny class where misclassification with tawny frequently occurs. The objectives of this study were to solve both the throughput and accuracy issues in the plant breeding workflow, develop a set of indices for distinguishing pubescence classes, and test a machine learning (ML) classification approach. A principal component analysis (PCA) on hyperspectral soybean plot data identified clusters related to pubescence classes, while a Jeffries-Matusita distance analysis indicated that all bands were important for pubescence class separability. Aerial images from 2018, 2019, and 2020 were analyzed in this study. A 60-plot test (2019) of genotypes with known pubescence was used as reference data, while whole-field images from 2018, 2019, and 2020 were used to examine the broad applicability of the classification methodology. Two indices, a red/blue ratio and blue normalized difference vegetation index (blue NDVI), were effective at differentiating tawny and gray pubescence types in high-resolution imagery. A ML approach using a support vector machine (SVM) radial basis function (RBF) classifier was able to differentiate the gray and tawny types (83.1% accuracy and kappa=0.740 on a pixel basis) on images where reference training data was present. The tested indices and ML model did not generalize across years to imagery that did not contain the reference training panel, indicating limitations of using aerial imagery for pubescence classification in some environmental conditions. High-throughput classification of gray and tawny pubescence types is possible using aerial imagery, but light tawny soybeans remain difficult to classify and may require training data from each field season.

scholarly journals Pemodelan Hujan Netto Berdasarkan Tutupan Lahan untuk Analisa Debit Aliran Rendah

2019 ◽  
Vol 4 (1) ◽  
pp. 1
Author(s):  
Adhi Yanuar Avianta ◽  
Rispiningtati Rispiningtati ◽  
Lily Montarcih Limantara ◽  
Ery Suhartanto
Keyword(s):  
Land Cover ◽  
Field Study ◽  
Land Cover Change ◽  
Satellite Images ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Canopy Interception ◽  
Volume Balance ◽  
Discharge Modeling

This research intends to investigate the land cover change and to obtain the canopy interception in the Lesti sub-watershed, and to produce the rainfall-discharge modeling as the function of net rainfall factor. The methodology consisted of identifying the land cover based on the Normalized Difference Vegetation Index (NDVI) classification of digital satellite images Landsat TM 7 and TM 8, carrying out the field study to obtain the canopy interception used a volume balance approach. The interception rate of Lesti sub-watershed are 5 – 7 % in everage of rainfall, the net-rainfall models of Lesti sub-watershed are Pnetto= P - (-1E07P² + 0.059P +0.260) for land clasification II and Pnetto = P – (-1E07P² + 0.199P + 0.16) for land clasification III, it used as the input on the rainfall-discharge modeling of F.J. Mock, the result showed that the use of net-rainfall on the rainfall-discharge modeling of F.J. Mock increased the accuracy of generated discharge which is strongly influenced by the proportional of land classification.

TEMPERATURA DE SUPERFÍCIE E A RELAÇÃO COM O ÍNDICE DE VEGETAÇÃO POR DIFERENÇA NORMALIZADA (NDVI) NA MICROBACIA DO RIO DA BATATEIRAS, CRATO-CE

2019 ◽  
Vol 21 (2) ◽  
pp. 1310-1320
Author(s):  
Cícera Celiane Januário da Silva ◽  
Vinicius Ferreira Luna ◽  
Joyce Ferreira Gomes ◽  
Juliana Maria Oliveira Silva
Keyword(s):  
Remote Sensing ◽  
Surface Temperature ◽  
Temperature Measurement ◽  
Rainy Season ◽  
Satellite Images ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Landsat 8 ◽  
Low Density ◽  
Difference Map

O objetivo do presente trabalho é fazer uma comparação entre a temperatura de superfície e o Índice de Vegetação por Diferença Normalizada (NDVI) na microbacia do rio da Batateiras/Crato-CE em dois períodos do ano de 2017, um chuvoso (abril) e um seco (setembro) como também analisar o mapa de diferença de temperatura nesses dois referidos períodos. Foram utilizadas imagens de satélite LANDSAT 8 (banda 10) para mensuração de temperatura e a banda 4 e 5 para geração do NDVI. As análises demonstram que no mês de abril a temperatura da superfície variou aproximadamente entre 23.2ºC e 31.06ºC, enquanto no mês correspondente a setembro, os valores variaram de 25°C e 40.5°C, sendo que as maiores temperaturas foram encontradas em locais com baixa densidade de vegetação, de acordo com a carta de NDVI desses dois meses. A maior diferença de temperatura desses dois meses foi de 14.2°C indicando que ocorre um aumento da temperatura proporcionado pelo período que corresponde a um dos mais secos da região, diferentemente de abril que está no período de chuvas e tem uma maior umidade, presença de vegetação e corpos d’água que amenizam a temperatura.Palavras-chave: Sensoriamento Remoto; Vegetação; Microbacia.                                                                                  ABSTRACTThe objective of the present work is to compare the surface temperature and the Normalized Difference Vegetation Index (NDVI) in the Batateiras / Crato-CE river basin in two periods of 2017, one rainy (April) and one (September) and to analyze the temperature difference map in these two periods. LANDSAT 8 (band 10) satellite images were used for temperature measurement and band 4 and 5 for NDVI generation. The analyzes show that in April the surface temperature varied approximately between 23.2ºC and 31.06ºC, while in the month corresponding to September, the values ranged from 25ºC and 40.5ºC, and the highest temperatures were found in locations with low density of vegetation, according to the NDVI letter of these two months. The highest difference in temperature for these two months was 14.2 ° C, indicating that there is an increase in temperature provided by the period that corresponds to one of the driest in the region, unlike April that is in the rainy season and has a higher humidity, presence of vegetation and water bodies that soften the temperature.Key-words: Remote sensing; Vegetation; Microbasin.RESUMENEl objetivo del presente trabajo es hacer una comparación entre la temperatura de la superficie y el Índice de Vegetación de Diferencia Normalizada (NDVI) en la cuenca Batateiras / Crato-CE en dos períodos de 2017, uno lluvioso (abril) y uno (Septiembre), así como analizar el mapa de diferencia de temperatura en estos dos períodos. Las imágenes de satélite LANDSAT 8 (banda 10) se utilizaron para la medición de temperatura y las bandas 4 y 5 para la generación de NDVI. Los análisis muestran que en abril la temperatura de la superficie varió aproximadamente entre 23.2ºC y 31.06ºC, mientras que en el mes correspondiente a septiembre, los valores oscilaron entre 25 ° C y 40.5 ° C, y las temperaturas más altas se encontraron en lugares con baja densidad de vegetación, según el gráfico NDVI de estos dos meses. La mayor diferencia de temperatura de estos dos meses fue de 14.2 ° C, lo que indica que hay un aumento en la temperatura proporcionada por el período que corresponde a uno de los más secos de la región, a diferencia de abril que está en la temporada de lluvias y tiene una mayor humedad, presencia de vegetación y cuerpos de agua que suavizan la temperatura.Palabras clave: Detección remota; vegetación; Cuenca.

scholarly journals NLOS Multipath Classification of GNSS Signal Correlation Output Using Machine Learning

Sensors ◽  
2021 ◽  
Vol 21 (7) ◽  
pp. 2503
Author(s):  
Taro Suzuki ◽  
Yoshiharu Amano
Keyword(s):  
Machine Learning ◽  
Satellite System ◽  
Training Data ◽  
Support Vector ◽  
Positioning Errors ◽  
Automated Method ◽  
Global Navigation Satellite ◽  
Better Than ◽  
Signal Correlation

This paper proposes a method for detecting non-line-of-sight (NLOS) multipath, which causes large positioning errors in a global navigation satellite system (GNSS). We use GNSS signal correlation output, which is the most primitive GNSS signal processing output, to detect NLOS multipath based on machine learning. The shape of the multi-correlator outputs is distorted due to the NLOS multipath. The features of the shape of the multi-correlator are used to discriminate the NLOS multipath. We implement two supervised learning methods, a support vector machine (SVM) and a neural network (NN), and compare their performance. In addition, we also propose an automated method of collecting training data for LOS and NLOS signals of machine learning. The evaluation of the proposed NLOS detection method in an urban environment confirmed that NN was better than SVM, and 97.7% of NLOS signals were correctly discriminated.

scholarly journals Mapping the Groundwater Level and Soil Moisture of a Montane Peat Bog Using UAV Monitoring and Machine Learning

2021 ◽  
Vol 13 (5) ◽  
pp. 907
Author(s):  
Theodora Lendzioch ◽  
Jakub Langhammer ◽  
Lukáš Vlček ◽  
Robert Minařík
Keyword(s):  
Machine Learning ◽  
Soil Moisture ◽  
Spatial Data ◽  
Groundwater Level ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Sampling Strategy ◽  
Peat Bog ◽  
Strong Impact ◽  
Ground Truth Data

One of the best preconditions for the sufficient monitoring of peat bog ecosystems is the collection, processing, and analysis of unique spatial data to understand peat bog dynamics. Over two seasons, we sampled groundwater level (GWL) and soil moisture (SM) ground truth data at two diverse locations at the Rokytka Peat bog within the Sumava Mountains, Czechia. These data served as reference data and were modeled with a suite of potential variables derived from digital surface models (DSMs) and RGB, multispectral, and thermal orthoimages reflecting topomorphometry, vegetation, and surface temperature information generated from drone mapping. We used 34 predictors to feed the random forest (RF) algorithm. The predictor selection, hyperparameter tuning, and performance assessment were performed with the target-oriented leave-location-out (LLO) spatial cross-validation (CV) strategy combined with forward feature selection (FFS) to avoid overfitting and to predict on unknown locations. The spatial CV performance statistics showed low (R2 = 0.12) to high (R2 = 0.78) model predictions. The predictor importance was used for model interpretation, where temperature had strong impact on GWL and SM, and we found significant contributions of other predictors, such as Normalized Difference Vegetation Index (NDVI), Normalized Difference Index (NDI), Enhanced Red-Green-Blue Vegetation Index (ERGBVE), Shape Index (SHP), Green Leaf Index (GLI), Brightness Index (BI), Coloration Index (CI), Redness Index (RI), Primary Colours Hue Index (HI), Overall Hue Index (HUE), SAGA Wetness Index (TWI), Plan Curvature (PlnCurv), Topographic Position Index (TPI), and Vector Ruggedness Measure (VRM). Additionally, we estimated the area of applicability (AOA) by presenting maps where the prediction model yielded high-quality results and where predictions were highly uncertain because machine learning (ML) models make predictions far beyond sampling locations without sampling data with no knowledge about these environments. The AOA method is well suited and unique for planning and decision-making about the best sampling strategy, most notably with limited data.

scholarly journals Validation of UAV-based alfalfa biomass predictability using photogrammetry with fully automatic plot segmentation

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Zhou Tang ◽  
Atit Parajuli ◽  
Chunpeng James Chen ◽  
Yang Hu ◽  
Samuel Revolinski ◽  
...  
Keyword(s):  
Prediction Model ◽  
High Throughput ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Selection Process ◽  
Forage Legume ◽  
Breeding Programs ◽  
High Throughput Phenotyping ◽  
Fully Automatic ◽  
Uav Images

AbstractAlfalfa is the most widely cultivated forage legume, with approximately 30 million hectares planted worldwide. Genetic improvements in alfalfa have been highly successful in developing cultivars with exceptional winter hardiness and disease resistance traits. However, genetic improvements have been limited for complex economically important traits such as biomass. One of the major bottlenecks is the labor-intensive phenotyping burden for biomass selection. In this study, we employed two alfalfa fields to pave a path to overcome the challenge by using UAV images with fully automatic field plot segmentation for high-throughput phenotyping. The first field was used to develop the prediction model and the second field to validate the predictions. The first and second fields had 808 and 1025 plots, respectively. The first field had three harvests with biomass measured in May, July, and September of 2019. The second had one harvest with biomass measured in September of 2019. These two fields were imaged one day before harvesting with a DJI Phantom 4 pro UAV carrying an additional Sentera multispectral camera. Alfalfa plot images were extracted by GRID software to quantify vegetative area based on the Normalized Difference Vegetation Index. The prediction model developed from the first field explained 50–70% (R Square) of biomass variation in the second field by incorporating four features from UAV images: vegetative area, plant height, Normalized Green–Red Difference Index, and Normalized Difference Red Edge Index. This result suggests that UAV-based, high-throughput phenotyping could be used to improve the efficiency of the biomass selection process in alfalfa breeding programs.

Sign in / Sign up

Export Citation Format

Share Document