Digital terrain model height estimation using support vector machine regression

Aim of study: The main objective is to determine the best machine-learning algorithm to classify the stand types of Monteverde forests combining LiDAR, orthophotography, and Sentinel-2 data, thus providing an easy and cheap method to classify Monteverde stand types.Area of study: 1500 ha forest in Monteverde, North Tenerife, Canary Islands.Material and methods: RF, SVML, SVMR and ANN algorithms are used to classify the three Monteverde stand types. Before training the model, feature selection of LiDAR, orthophotography, and Sentinel-2 data through VSURF was carried out. Comparison of its accuracy was performed.Main results: Five LiDAR variables were found to be the most efficient for classifying each object, while only one Sentinel-2 index and one Sentinel-2 band was valuable. Additionally, standard deviation and mean of the Red orthophotography colour band, and ratio between Red and Green bands were also found to be suitable. SVML is confirmed as the most accurate algorithm (0.904, 0.041 SD) while ANN showed the lowest value of 0.891 (0.073 SD). SVMR and RF obtain 0.902 (0.060 SD) and 0.904 (0.056 SD) respectively. SVML was found to be the best method given its low standard deviation.Research highlights: The similar high accuracy values among models confirm the importance of taking into account diverse machine-learning methods for stand types classification purposes and different explanatory variables. Although differences between errors may not seem relevant at a first glance, due to the limited size of the study area with only three plus two categories, such differences could be highly important when working at large scales with more stand types.ADDITIONAL KEY WORDSRF algorithm, SVML algorithm, SVMR algorithm, ANN algorithm, LiDAR, orthophotography, Sentinel-2ABBREVIATIONS USEDANN, artificial neural networks algorithm; Band04, Sentinel-2 band 04 image data; BR, brezal; DTHM, digital tree height model; DTHM-2016, digital tree height model based on 2016 LiDAR data; DTM, digital terrain model; DTM-2016, digital terrain model based on 2016 LiDAR data; FBA, fayal-brezal-acebiñal; FCC, canopy cover; HEIGHT-2009, maximum height based on 2009 LiDAR data; HGR, height growth based on 2009 and 2016 LiDAR data; LA, laurisilva; NDVI705, Sentinel-2 index image data; NMF, non-Monteverde forest; NMG, non-Monteverde ground; P95-2016, height percentile 95 based on 2016 LiDAR data; RATIO R/G, ratio between Red and Green bands orthophotograph data; RED, Red band orthophotograph data; Red-SD, standard deviation of the Red band orthophotograph data; RF, random forest algorithm; SVM, support vector machine algorithm; SVML, linear support vector machine algorithm; SVMR, radial support vector machine algorithm; VSURF, variable selection using random forest.

Download Full-text

Semiautomated object-based classification of rain-induced landslides with VHR multispectral images on Madeira Island

Natural Hazards and Earth System Science ◽

10.5194/nhess-16-1035-2016 ◽

2016 ◽

Vol 16 (4) ◽

pp. 1035-1048 ◽

Cited By ~ 11

Author(s):

Sandra Heleno ◽

Magda Matias ◽

Pedro Pina ◽

António Jorge Sousa

Keyword(s):

Digital Terrain Model ◽

Support Vector ◽

Commission Errors ◽

Madeira Island ◽

Terrain Model ◽

Object Based Image Analysis ◽

Digital Terrain ◽

Object Based ◽

Landslide Event ◽

Separate Source

Abstract. A method for semiautomated landslide detection and mapping, with the ability to separate source and run-out areas, is presented in this paper. It combines object-based image analysis and a support vector machine classifier and is tested using a GeoEye-1 multispectral image, sensed 3 days after a major damaging landslide event that occurred on Madeira Island (20 February 2010), and a pre-event lidar digital terrain model. The testing is developed in a 15 km2 wide study area, where 95 % of the number of landslides scars are detected by this supervised approach. The classifier presents a good performance in the delineation of the overall landslide area, with commission errors below 26 % and omission errors below 24 %. In addition, fair results are achieved in the separation of the source from the run-out landslide areas, although in less illuminated slopes this discrimination is less effective than in sunnier, east-facing slopes.

Download Full-text

Geographic information system (GIS) procedure for preliminary delineation of debris-flow hazard areas from a digital terrain model, Madison County, Virginia

Open-File Report ◽

10.3133/ofr99336 ◽

1999 ◽

Author(s):

R.H. Campbell ◽

P.G. Chirico

Keyword(s):

Information System ◽

Geographic Information System ◽

Debris Flow ◽

Digital Terrain Model ◽

Geographic Information ◽

Terrain Model ◽

Madison County ◽

Digital Terrain ◽

Debris Flow Hazard

Download Full-text

The Effect of LiDAR Sampling Density on DTM Accuracy for Areas with Heavy Forest Cover

Forests ◽

10.3390/f12030265 ◽

2021 ◽

Vol 12 (3) ◽

pp. 265

Author(s):

Mihnea Cățeanu ◽

Arcadie Ciubotaru

Keyword(s):

Forest Cover ◽

Initial Point ◽

Ground Surface ◽

Digital Terrain Model ◽

Morphological Data ◽

Sampling Density ◽

Terrain Model ◽

Digital Terrain ◽

Point Density ◽

The Impact

Laser scanning via LiDAR is a powerful technique for collecting data necessary for Digital Terrain Model (DTM) generation, even in densely forested areas. LiDAR observations located at the ground level can be separated from the initial point cloud and used as input for the generation of a Digital Terrain Model (DTM) via interpolation. This paper proposes a quantitative analysis of the accuracy of DTMs (and derived slope maps) obtained from LiDAR data and is focused on conditions common to most forestry activities (rough, steep terrain with forest cover). Three interpolation algorithms were tested: Inverse Distance Weighted (IDW), Natural Neighbour (NN) and Thin-Plate Spline (TPS). Research was mainly focused on the issue of point data density. To analyze its impact on the quality of ground surface modelling, the density of the filtered data set was artificially lowered (from 0.89 to 0.09 points/m2) by randomly removing point observations in 10% increments. This provides a comprehensive method of evaluating the impact of LiDAR ground point density on DTM accuracy. While the reduction of point density leads to a less accurate DTM in all cases (as expected), the exact pattern varies by algorithm. The accuracy of the LiDAR-derived DTMs is relatively good even when LiDAR sampling density is reduced to 0.40–0.50 points/m2 (50–60 % of the initial point density), as long as a suitable interpolation algorithm is used (as IDW proved to be less resilient to density reductions below approximately 0.60 points/m2). In the case of slope estimation, the pattern is relatively similar, except the difference in accuracy between IDW and the other two algorithms is even more pronounced than in the case of DTM accuracy. Based on this research, we conclude that LiDAR is an adequate method for collecting morphological data necessary for modelling the ground surface, even when the sampling density is significantly reduced.

Download Full-text

Support vector machine regression for predicting dimensional features of die-sinking electrical discharge machined components

Procedia CIRP ◽

10.1016/j.procir.2021.03.109 ◽

2021 ◽

Vol 99 ◽

pp. 508-513

Author(s):

Kanka Goswami ◽

G L Samuel

Keyword(s):

Support Vector Machine ◽

Electrical Discharge ◽

Support Vector ◽

Support Vector Machine Regression

Download Full-text

DTM-based analysis of the spatial distribution of topolineaments

Open Geosciences ◽

10.1515/geo-2020-0059 ◽

2020 ◽

Vol 12 (1) ◽

pp. 1185-1199

Author(s):

Mirosław Kamiński

Keyword(s):

Laser Scanning ◽

Digital Terrain Model ◽

Research Area ◽

Tectonic Structures ◽

Empirical Bayesian ◽

Scanning Method ◽

Empirical Bayesian Kriging ◽

Terrain Model ◽

Digital Terrain ◽

Airborne Laser

AbstractThe research area is located on the boundary between two Paleozoic structural units: the Radom–Kraśnik Block and the Mazovian–Lublin Basin in the southeastern Poland. The tectonic structures are separated by the Ursynów–Kazimierz Dolny fault zone. The digital terrain model obtained by the ALS (Airborne Laser Scanning) method was used. Classification and filtration of an elevation point cloud were performed. Then, from the elevation points representing only surfaces, a digital terrain model was generated. The model was used to visually interpret the course of topolineaments and their automatic extraction from DTM. Two topolineament systems, trending NE–SW and NW–SE, were interpreted. Using the kernel density algorithm, topolineament density models were generated. Using the Empirical Bayesian Kriging, a thickness model of quaternary deposits was generated. A relationship was observed between the course of topolineaments and the distribution and thickness of Quaternary formations. The topolineaments were compared with fault directions marked on tectonic maps of the Paleozoic and Mesozoic. Data validation showed consistency between topolineaments and tectonic faults. The obtained results are encouraging for further research.

Download Full-text

Production, Validation and Morphometric Analysis of a Digital Terrain Model for Lake Trichonis Using Geospatial Technologies and Hydroacoustics

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi10020091 ◽

2021 ◽

Vol 10 (2) ◽

pp. 91

Author(s):

Triantafyllia-Maria Perivolioti ◽

Antonios Mouratidis ◽

Dimitrios Terzopoulos ◽

Panagiotis Kalaitzis ◽

Dimitrios Ampatzidis ◽

...

Keyword(s):

Morphometric Analysis ◽

Ad Hoc ◽

Regional Scale ◽

Digital Terrain Model ◽

Relevant Information ◽

Relative Difference ◽

Systematic Observation ◽

Qualitative And Quantitative ◽

Terrain Model ◽

Digital Terrain

Covering an area of approximately 97 km2 and with a maximum depth of 58 m, Lake Trichonis is the largest and one of the deepest natural lakes in Greece. As such, it constitutes an important ecosystem and freshwater reserve at the regional scale, whose qualitative and quantitative properties ought to be monitored. Depth is a crucial parameter, as it is involved in both qualitative and quantitative monitoring aspects. Thus, the availability of a bathymetric model and a reliable DTM (Digital Terrain Model) of such an inland water body is imperative for almost any systematic observation scenario or ad hoc measurement endeavor. In this context, the purpose of this study is to produce a DTM from the only official cartographic source of relevant information available (dating back approximately 70 years) and evaluate its performance against new, independent, high-accuracy hydroacoustic recordings. The validation procedure involves the use of echosoundings coupled with GPS, and is followed by the production of a bathymetric model for the assessment of the discrepancies between the DTM and the measurements, along with the relevant morphometric analysis. Both the production and validation of the DTM are conducted in a GIS environment. The results indicate substantial discrepancies between the old DTM and contemporary acoustic data. A significant overall deviation of 3.39 ± 5.26 m in absolute bottom elevation differences and 0.00 ± 7.26 m in relative difference residuals (0.00 ± 2.11 m after 2nd polynomial model corrector surface fit) of the 2019 bathymetric dataset with respect to the ~1950 lake DTM and overall morphometry appear to be associated with a combination of tectonics, subsidence and karstic phenomena in the area. These observations could prove useful for the tectonics, geodynamics and seismicity with respect to the broader Corinth Rift region, as well as for environmental management and technical interventions in and around the lake. This dictates the necessity for new, extensive bathymetric measurements in order to produce an updated DTM of Lake Trichonis, reflecting current conditions and tailored to contemporary accuracy standards and state-of-the-art research in various disciplines in and around the lake.

Download Full-text

Refinement of interferometric SAR parameters using digital terrain model as an external reference

ISPRS Journal of Photogrammetry and Remote Sensing ◽

10.1016/j.isprsjprs.2021.02.017 ◽

2021 ◽

Vol 175 ◽

pp. 34-43

Author(s):

Jyunpei Uemoto

Keyword(s):

Digital Terrain Model ◽

Terrain Model ◽

Digital Terrain ◽

External Reference ◽

Interferometric Sar

Download Full-text

Modeling Streamflow and Sediment Loads with a Photogrammetrically Derived UAS Digital Terrain Model: Empirical Evaluation from a Fluvial Aggregate Excavation Operation

Drones ◽

10.3390/drones5010020 ◽

2021 ◽

Vol 5 (1) ◽

pp. 20

Author(s):

Joseph P. Hupy ◽

Cyril O. Wilson

Keyword(s):

Soil Erosion ◽

Point Cloud ◽

Empirical Evaluation ◽

Digital Terrain Model ◽

Surface Flow ◽

Sediment Loading ◽

Terrain Model ◽

Digital Terrain ◽

Statistical Measures ◽

Geospatial Datasets

Soil erosion monitoring is a pivotal exercise at macro through micro landscape levels, which directly informs environmental management at diverse spatial and temporal scales. The monitoring of soil erosion can be an arduous task when completed through ground-based surveys and there are uncertainties associated with the use of large-scale medium resolution image-based digital elevation models for estimating erosion rates. LiDAR derived elevation models have proven effective in modeling erosion, but such data proves costly to obtain, process, and analyze. The proliferation of images and other geospatial datasets generated by unmanned aerial systems (UAS) is increasingly able to reveal additional nuances that traditional geospatial datasets were not able to obtain due to the former’s higher spatial resolution. This study evaluated the efficacy of a UAS derived digital terrain model (DTM) to estimate surface flow and sediment loading in a fluvial aggregate excavation operation in Waukesha County, Wisconsin. A nested scale distributed hydrologic flow and sediment loading model was constructed for the UAS point cloud derived DTM. To evaluate the effectiveness of flow and sediment loading generated by the UAS point cloud derived DTM, a LiDAR derived DTM was used for comparison in consonance with several statistical measures of model efficiency. Results demonstrate that the UAS derived DTM can be used in modeling flow and sediment erosion estimation across space in the absence of a LiDAR-based derived DTM.

Download Full-text