scholarly journals Farmland Parcel Mapping in Mountain Areas Using Time-Series SAR Data and VHR Optical Images

2020 ◽  
Vol 12 (22) ◽  
pp. 3733
Author(s):  
Wei Liu ◽  
Jian Wang ◽  
Jiancheng Luo ◽  
Zhifeng Wu ◽  
Jingdong Chen ◽  
...  
Keyword(s):  
Time Series ◽  
Time Profile ◽  
Classification Method ◽  
Guizhou Province ◽  
Optical Data ◽  
Time Series Classification ◽  
Mountainous Areas ◽  
Mountain Areas ◽  
Actual Distribution ◽  
Sar Data

Accurate, timely, and reliable farmland mapping is a prerequisite for agricultural management and environmental assessment in mountainous areas. However, in these areas, high spatial heterogeneity and diversified planting structures together generate various small farmland parcels with irregular shapes that are difficult to accurately delineate. In addition, the absence of optical data caused by the cloudy and rainy climate impedes the use of time-series optical data to distinguish farmland from other land use types. Automatic delineation of farmland parcels in mountain areas is still a very difficult task. This paper proposes an innovative precise farmland parcel extraction approach supported by very high resolution(VHR) optical image and time series synthetic aperture radar(SAR) data. Firstly, Google satellite imagery with a spatial resolution of 0.55 m was used for delineating the boundaries of ground parcel objects in mountainous areas by a hierarchical extraction scheme. This scheme divides farmland into four types based on the morphological features presented in optical imagery, and designs different extraction models to produce each farmland type, respectively. The potential farmland parcel distribution map is then obtained by the layered recombination of these four farmland types. Subsequently, the time profile of each parcel in this map was constructed by five radar variables from the Sentinel-1A dataset, and the time-series classification method was used to distinguish farmland parcels from other types. An experiment was carried out in the north of Guiyang City, Guizhou Province, Southwest China. The result shows that, the producer’s accuracy of farmland parcels obtained by the hierarchical scheme is increased by 7.39% to 96.38% compared with that without this scheme, and the time-series classification method produces an accuracy of 80.83% to further obtain the final overall accuracy of 96.05% for the farmland parcel maps, showing a good performance. In addition, through visual inspection, this method has a better suppression effect on background noise in mountainous areas, and the extracted farmland parcels are closer to the actual distribution of the ground farmland.

scholarly journals A Metric Learning-Based Univariate Time Series Classification Method

Information ◽  
2020 ◽  
Vol 11 (6) ◽  
pp. 288
Author(s):  
Kuiyong Song ◽  
Nianbin Wang ◽  
Hongbin Wang
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Multivariate Time Series ◽  
Metric Learning ◽  
Classification Method ◽  
Series Data ◽  
Classification Error ◽  
Time Series Classification ◽  
Classification Error Rate ◽  
Univariate Time Series

High-dimensional time series classification is a serious problem. A similarity measure based on distance is one of the methods for time series classification. This paper proposes a metric learning-based univariate time series classification method (ML-UTSC), which uses a Mahalanobis matrix on metric learning to calculate the local distance between multivariate time series and combines Dynamic Time Warping(DTW) and the nearest neighbor classification to achieve the final classification. In this method, the features of the univariate time series are presented as multivariate time series data with a mean value, variance, and slope. Next, a three-dimensional Mahalanobis matrix is obtained based on metric learning in the data. The time series is divided into segments of equal intervals to enable the Mahalanobis matrix to more accurately describe the features of the time series data. Compared with the most effective measurement method, the related experimental results show that our proposed algorithm has a lower classification error rate in most of the test datasets.

scholarly journals Combined Use of Optical and Synthetic Aperture Radar Data for REDD+ Applications in Malawi

Land ◽  
2018 ◽  
Vol 7 (4) ◽  
pp. 116 ◽  
Author(s):  
Manuela Hirschmugl ◽  
Carina Sobe ◽  
Janik Deutscher ◽  
Mathias Schardt
Keyword(s):  
Time Series ◽  
Land Cover ◽  
Synthetic Aperture Radar ◽  
Data Availability ◽  
Synthetic Aperture ◽  
Optical Data ◽  
Series Data ◽  
Forest Mapping ◽  
Sar Data ◽  
Aperture Radar

Recent developments in satellite data availability allow tropical forest monitoring to expand in two ways: (1) dense time series foster the development of new methods for mapping and monitoring dry tropical forests and (2) the combination of optical data and synthetic aperture radar (SAR) data reduces the problems resulting from frequent cloud cover and yields additional information. This paper covers both issues by analyzing the possibilities of using optical (Sentinel-2) and SAR (Sentinel-1) time series data for forest and land cover mapping for REDD+ (Reducing Emissions from Deforestation and Forest Degradation) applications in Malawi. The challenge is to combine these different data sources in order to make optimal use of their complementary information content. We compare the results of using different input data sets as well as of two methods for data combination. Results show that time-series of optical data lead to better results than mono-temporal optical data (+8% overall accuracy for forest mapping). Combination of optical and SAR data leads to further improvements: +5% in overall accuracy for land cover and +1.5% for forest mapping. With respect to the tested combination methods, the data-based combination performs slightly better (+1% overall accuracy) than the result-based Bayesian combination.

scholarly journals A T-CNN Time Series Classification Method

2021 ◽  
Author(s):  
Junlu Wang ◽  
Su Li ◽  
Wanting Ji ◽  
Tian Jiang ◽  
Baoyan Song
Keyword(s):  
Time Series ◽  
Classification Accuracy ◽  
Transformation Method ◽  
Streaming Data ◽  
Classification Method ◽  
Gram Matrix ◽  
Event Analysis ◽  
Time Series Classification ◽  
Basic Task ◽  
Low Efficiency

Abstract Time series classification is a basic task in the field of streaming data event analysis and data mining. The existing time series classification methods have the problems of low classification accuracy and low efficiency. To solve these problems, this paper proposes a T-CNN time series classification method based on a Gram matrix. Specifically, we perform wavelet threshold denoising on time series to filter normal curve noise, and propose a lossless transformation method based on the Gram matrix, which converts the time series to the time domain image and retains all the information of events. Then, we propose an improved CNN time series classification method, which introduces the Toeplitz convolution kernel matrix into convolution layer calculation. Finally, we introduce a Triplet network to calculate the similarity between similar events and different classes of events, and optimize the squared loss function of CNN. The proposed T-CNN model can accelerate the convergence rate of gradient descent and improve classification accuracy. Experimental results show that, compared with the existing methods, our T-CNN time series classification method has great advantages in efficiency and accuracy.

Multisensor SAR and optical estimation of grassland above-ground biomass and LAI: a case study for the Mazia valley in South Tyrol

2021 ◽  
Author(s):  
Mattia Rossi ◽  
Eugenia Chiarito ◽  
Francesca Cigna ◽  
Giovanni Cuozzo ◽  
Giacomo Fontanelli ◽  
...  
Keyword(s):  
Ecosystem Services ◽  
Management Practices ◽  
Optical Data ◽  
Support Vector ◽  
Above Ground Biomass ◽  
Mountainous Areas ◽  
South Tyrol ◽  
Ground Biomass ◽  
Grassland Type ◽  
Sar Data

<p>Grasslands are a predominant land cover form, responsible for ecosystem services such as slope stabilization, water and carbon storage or fodder provision for livestock. At the same time, altering climatic effects and human activities have influenced the natural growth pattern and condition of alpine grasslands over the past decades. Mountainous areas are projected to be particularly impacted by climatic changes and management practices. Nowadays, a wide variety and different installations of Earth observation systems are available to monitor and predict grassland growth and status, to evidence ecosystem services such as biodiversity, the fodder availability or to highlight the effectiveness of management practices.</p><p>In this study Support Vector Regression (SVR) and Random Forest (RF) machine learning techniques were used to estimate the aboveground biomass, plant water content and the leaf area index (LAI). As input, we combined hyperspectral imagery from field spectrometers, optical Sentinel-2 data as well as SAR data from Sentinel-1. The models were tested targeting approximately 250 biomass and LAI samples taken from 2017 to 2020 on grasslands in the Mazia/Matsch valley, located in South Tyrol (Italy). The dataset was divided based on grassland type (meadow and pasture) the growth period (up to three growth periods a year for meadows), as well as the year, to analyze the modelled predictions based on the growing stage of the vegetation.</p><p>The results obtained using the integration of the datasets are very promising in the meadow, with R<sup>2</sup> reaching ranging from 0.5 to 0.8 for the biomass and from 0.6 to 0.8 for the LAI retrieval. At the same time, the division in growth phases shows a slightly higher correlation than during the first and second growing periods, indicating that the irregular growth after the last harvest of the year affects the capability of prediction of LAI and above-ground biomass. However, the predictability worsens on high biomass and LAI values before the harvest takes place, thus indicating an impact of the saturation in the optical data and revealing the need for additional data sources or an alternated weighting of the predictors in the models. The results on the pasture show that the prediction of LAI and biomass with optical and SAR data is difficult to achieve (mean R<sup>2</sup> ranging from 0.3 to 0.4) given the natural heterogeneity in growth within the test area. Additional datasets such as cattle movement or the slope information could represent a valuable source of information for further LAI and biomass growth analyses in mountainous areas.</p><p>This research is part of the 2019-2021 project ‘Development of algorithms for estimation and monitoring of hydrological parameters from satellite and drone’, funded by ASI under grant agreement n.2018-37-HH.0.</p>

Sign in / Sign up

Export Citation Format

Share Document