Testing random forest classification for identifying lava flows and mapping age groups on a single Landsat 8 image

Abstract

Mapping lava flows using satellite images is an important application of remote sensing in volcanology. Several volcanoes have been mapped through remote sensing using a wide range of data, from optical to thermal infrared and radar images, using techniques such as manual mapping, supervised/unsupervised classification, and elevation subtraction. So far, spectralbased mapping applications mainly focus on the use of traditional pixel-based classifiers, without much investigation into the added value of object-based approaches and into advantages of using machine learning algorithms. In this study, Nyamuragira, characterized by a series of more than 20 overlapping lava flows erupted over the last century, was used as a case study. The random forest classifier was tested to map lava flows based on pixels and objects. Image classification was conducted for the 20 individual flows and for 8 groups of flows of similar age using Landsat 8 imagery and a DEM of the volcano, both at 30-meter spatial resolution. Results show that object-based classification produces maps with continuous and homogeneous lava surfaces, in agreement with the physical characteristics of lava flows, while lava flows mapped through the pixel-based classification are heterogeneous and fragmented including much "salt and pepper 2 noise". In terms of accuracy, both pixel-based and object-based classification performs well but the former results in higher accuracies than the latter except for mapping lava flow age groups without using topographic features. It is concluded that despite spectral similarity, lava flows of contrasting age can be well discriminated and mapped by means of image classification. The classification approach demonstrated in this study only requires easily accessible image data and can be applied to other volcanoes as well if there is sufficient information to calibrate the mapping.

Mapping and Characterizing Spatiotemporal Dynamics of Impervious Surfaces Using Landsat Images: A Case Study of Xuzhou, East China from 1995 to 2018

“…To further assess the accuracy of impervious surface mapping, it is necessary to investigate the agreement between the mapped and real impervious surface fractions. Although the confusion matrix and Kappa coefficient are the commonly used accuracy assessment approaches [48,49], they are suitable for categorical variables, such as land cover classes from image classification. Impervious surface fractions are, however, continuous variables, and it would be more interesting to compare the mapped impervious surface fractions with real ones which were obtained from image digitalization and evaluate how close they would be [50,51].…”

Geochemical Discrimination and Characteristics of Magmatic Tectonic Settings: A Machine‐Learning‐Based Approach

“…The results of our discrimination analysis are presented with the associated feature quantities that are then geochemically interpreted in the discussion. Machine learning methods such as the SVM and RF are increasingly being used in the Earth sciences (Belgiu & Drăguţ, ; Cracknell & Reading, ; Li et al, ; Petrelli & Perugini, ; Rouet‐Leduc et al, ), although to our knowledge the SMR has not previously been used with geochemical data. The SMR yields sparse solutions and our results indicate that this technique successfully identified both elements and isotopes that can be effectively used to discriminate between different tectonic settings.…”

Discriminating Urban Forest Types from Sentinel-2A Image Data through Linear Spectral Mixture Analysis: A Case Study of Xuzhou, East China

“…These classifications were performed using the same training samples and assessed using validation data as the four SVM classifications in Table 4. For both RF classifications, their optimal mtry and ntry values were 1000 and 22 based on the result of out-of-bag error (OOB) test (see its definition in Li et al (2017) [76]). The QUEST is a type of decision tree classifier and has a faster calculation and higher accuracy than other types [77].…”