scholarly journals Lowland Rice Mapping in Sédhiou Region (Senegal) Using Sentinel 1 and Sentinel 2 Data and Random Forest

2020 ◽  
Vol 12 (20) ◽  
pp. 3403 ◽  
Author(s):  
Edoardo Fiorillo ◽  
Edmondo Di Giuseppe ◽  
Giacomo Fontanelli ◽  
Fabio Maselli
Keyword(s):  
Time Series ◽  
Random Forest ◽  
Land Cover ◽  
Technical Assistance ◽  
Lowland Rice ◽  
Ratio Estimator ◽  
Study Region ◽  
Ground Sample ◽  
Ndvi Time Series ◽  
Sentinel 2

In developing countries, information on the area and spatial distribution of paddy rice fields is an essential requirement for ensuring food security and facilitating targeted actions of both technical assistance and restoration of degraded production areas. In this study, Sentinel 1 (S1) and Sentinel 2 (S2) imagery was used to map lowland rice crop areas in the Sédhiou region (Senegal) for the 2017, 2018, and 2019 growing seasons using the Random Forest (RF) algorithm. Ground sample datasets were annually collected (416, 455, and 400 samples) for training and testing yearly RF classification. A procedure was preliminarily applied to process S2 scenes and yield a normalized difference vegetation index (NDVI) time series less affected by clouds. A total of 93 predictors were calculated from S2 NDVI time series and S1 vertical transmit–horizontal receive (VH) and vertical transmit–vertical receive (VV) backscatters. Guided regularized random forest (GRRF) was used to deal with the arising multicollinearity and identify the most important predictors. The RF classifier was then applied to the selected predictors. The algorithm predicted the five land cover types present in the test areas, with a maximum accuracy of 87% and kappa coefficient of 0.8 in 2019. The broad land cover maps identified around 12,500 (2017), 13,800 (2018), and 12,800 (2019) ha of lowland rice crops. The study highlighted a partial difficulty of the classifier to distinguish rice from natural herbaceous vegetation (NHV) due to similar temporal patterns and high intra-class variability. Moreover, the results of this investigation indicated that S2-derived predictors provided more valuable information compared to VV and VH backscatter-derived predictors, but a combination of radar and optical imagery always outperformed a classification based on single-sensor inputs. An example is finally provided that illustrates how the maps obtained can be combined with ground observations through a ratio estimator in order to yield a statistically sound prediction of rice area all over the study region.

scholarly journals Land Cover Classification of an Area Susceptible to Landslides Using Random Forest and NDVI Time Series Data

2020 ◽  
Author(s):  
Tatiana Dias Tardelli Uehara ◽  
Anderson Reis Soares ◽  
Renata Pacheco Quevedo ◽  
Thales Sehn Korting ◽  
Leila Maria Garcia Fonseca ◽  
...  
Keyword(s):  
Time Series ◽  
Random Forest ◽  
Land Cover ◽  
Time Series Data ◽  
Land Cover Classification ◽  
Series Data ◽  
Ndvi Time Series

Channel-Based Attention for Land Cover Classification using Sentinel-2 Time Series

2021 ◽  
Author(s):  
H. Courteille ◽  
A. Benoit ◽  
N. Meger ◽  
A. Atto ◽  
D. Ienco
Keyword(s):  
Time Series ◽  
Land Cover ◽  
Land Cover Classification ◽  
Sentinel 2

scholarly journals Assessing Spatial Limits of Sentinel-2 Data on Arable Crops in the Context of Checks by Monitoring

2020 ◽  
Vol 12 (14) ◽  
pp. 2195 ◽  
Author(s):  
Blanka Vajsová ◽  
Dominique Fasbender ◽  
Csaba Wirnhardt ◽  
Slavko Lemajic ◽  
Wim Devos
Keyword(s):  
Time Series ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Policy Framework ◽  
Pixel Size ◽  
Control Approach ◽  
Continuous State ◽  
Ndvi Time Series ◽  
High Level ◽  
Sentinel 2

The availability of large amounts of Sentinel-2 data has been a trigger for its increasing exploitation in various types of applications. It is, therefore, of importance to understand the limits above which these data still guarantee a meaningful outcome. This paper proposes a new method to quantify and specify restrictions of the Sentinel-2 imagery in the context of checks by monitoring, a newly introduced control approach within the European Common Agriculture Policy framework. The method consists of a comparison of normalized difference vegetation index (NDVI) time series constructed from data of different spatial resolution to estimate the performance and limits of the coarser one. Using similarity assessment of Sentinel-2 (10 m pixel size) and PlanetScope (3 m pixel size) NDVI time series, it was estimated that for 10% out of 867 fields less than 0.5 ha in size, Sentinel-2 data did not provide reliable evidence of the activity or state of the agriculture field over a given timeframe. Statistical analysis revealed that the number of clean or full pixels and the proportion of pixels lost after an application of a 5-m (1/2 pixel) negative buffer are the geospatial parameters of the field that have the highest influence on the ability of the Sentinel-2 data to qualify the field’s state in time. We specified the following limiting criteria: at least 8 full pixels inside a border and less than 60% of pixels lost. It was concluded that compliance with the criteria still assures a high level of extracted information reliability. Our research proved the promising potential, which was higher than anticipated, of Sentinel-2 data for the continuous state assessment of small fields. The method could be applied to other sensors and indicators.

scholarly journals Land Cover Classification using Google Earth Engine and Random Forest Classifier—The Role of Image Composition

2020 ◽  
Vol 12 (15) ◽  
pp. 2411 ◽  
Author(s):  
Thanh Noi Phan ◽  
Verena Kuch ◽  
Lukas W. Lehnert
Keyword(s):  
Time Series ◽  
Random Forest ◽  
Land Cover ◽  
Land Cover Classification ◽  
High Accuracy ◽  
Google Earth ◽  
Temporal Aggregation ◽  
Google Earth Engine ◽  
Time Series Images ◽  
Land Cover Maps

Land cover information plays a vital role in many aspects of life, from scientific and economic to political. Accurate information about land cover affects the accuracy of all subsequent applications, therefore accurate and timely land cover information is in high demand. In land cover classification studies over the past decade, higher accuracies were produced when using time series satellite images than when using single date images. Recently, the availability of the Google Earth Engine (GEE), a cloud-based computing platform, has gained the attention of remote sensing based applications where temporal aggregation methods derived from time series images are widely applied (i.e., the use the metrics such as mean or median), instead of time series images. In GEE, many studies simply select as many images as possible to fill gaps without concerning how different year/season images might affect the classification accuracy. This study aims to analyze the effect of different composition methods, as well as different input images, on the classification results. We use Landsat 8 surface reflectance (L8sr) data with eight different combination strategies to produce and evaluate land cover maps for a study area in Mongolia. We implemented the experiment on the GEE platform with a widely applied algorithm, the Random Forest (RF) classifier. Our results show that all the eight datasets produced moderately to highly accurate land cover maps, with overall accuracy over 84.31%. Among the eight datasets, two time series datasets of summer scenes (images from 1 June to 30 September) produced the highest accuracy (89.80% and 89.70%), followed by the median composite of the same input images (88.74%). The difference between these three classifications was not significant based on the McNemar test (p > 0.05). However, significant difference (p < 0.05) was observed for all other pairs involving one of these three datasets. The results indicate that temporal aggregation (e.g., median) is a promising method, which not only significantly reduces data volume (resulting in an easier and faster analysis) but also produces an equally high accuracy as time series data. The spatial consistency among the classification results was relatively low compared to the general high accuracy, showing that the selection of the dataset used in any classification on GEE is an important and crucial step, because the input images for the composition play an essential role in land cover classification, particularly with snowy, cloudy and expansive areas like Mongolia.

scholarly journals Land Cover Change Detection Using Multiple Shape Parameters of Spectral and NDVI Curves

2018 ◽  
Vol 10 (8) ◽  
pp. 1251 ◽  
Author(s):  
Boyu Liu ◽  
Jun Chen ◽  
Jiage Chen ◽  
Weiwei Zhang
Keyword(s):  
Time Series ◽  
Land Cover ◽  
Change Detection ◽  
Land Cover Change ◽  
Shape Features ◽  
Shape Parameters ◽  
Shape Information ◽  
Zero Crossing ◽  
Ndvi Time Series ◽  
Land Cover Change Detection

Spectral and NDVI values have been used to calculate the change magnitudes of land cover, but may result in many pseudo-changes because of inter-class variance. Recently, the shape information of spectral or NDVI curves such as direction, angle, gradient, or other mathematical indicators have been used to improve the accuracy of land cover change detection. However, these measurements, in terms of the single shape features, can hardly capture the complete trends of curves affected by the unsynchronized phenology. Therefore, the calculated change magnitudes are indistinct such that changes and no-changes have a low contrast. This problem has prevented traditional change detection methods from achieving a higher accuracy using bi-temporal images or NDVI time series. In this paper, a multiple shape parameters-based change detection method is proposed by combining the spectral correlation operator and the shape features of NDVI temporal curves (phase angle cumulant, baseline cumulant, relative cumulation rate, and zero-crossing rate). The change magnitude is derived by integrating all the inter-annual differences of these shape parameters. The change regions are discriminated by an automated threshold selection method known as histogram concavity analysis. The results showed that the mean differences in the change magnitudes of the proposed method between 2100 changed and 2523 unchanged pixels was 32%, the overall accuracy was approximately 88%, and the kappa coefficient was 0.76. A comparative analysis was conducted with bi-temporal image-based methods and NDVI time series-based methods, and we demonstrate that the proposed method is more effective and robust than traditional methods in achieving high-contrast change magnitudes and accuracy.

scholarly journals Early-season crop mapping using improved artificial immune network (IAIN) and Sentinel data

PeerJ ◽  
2018 ◽  
Vol 6 ◽  
pp. e5431 ◽  
Author(s):  
Pengyu Hao ◽  
Huajun Tang ◽  
Zhongxin Chen ◽  
Zhengjia Liu
Keyword(s):  
Time Series ◽  
Winter Wheat ◽  
Vegetation Index ◽  
Immune Network ◽  
Artificial Immune ◽  
Study Region ◽  
Early Season ◽  
Spring Maize ◽  
Artificial Immune Network ◽  
Sentinel 2

Substantial efforts have been made to identify crop types by region, but few studies have been able to classify crops in early season, particularly in regions with heterogeneous cropping patterns. This is because image time series with both high spatial and temporal resolution contain a number of irregular time series, which cannot be identified by most existing classifiers. In this study, we firstly proposed an improved artificial immune network (IAIN), and tried to identify major crops in Hengshui, China at early season using IAIN classifier and short image time series. A time series of 15-day composited images was generated from 10 m spatial resolution Sentinel-1 and Sentinel-2 data. Near-infrared (NIR) band and normalized difference vegetation index (NDVI) were selected as optimal bands by pair-wise Jeffries–Matusita distances and Gini importance scores calculated from the random forest algorithm. When using IAIN to identify irregular time series, overall accuracy of winter wheat and summer crops were 99% and 98.55%, respectively. We then used the IAIN classifier and NIR and NDVI time series to identify major crops in the study region. Results showed that winter wheat could be identified 20 days before harvest, as both the producer’s accuracy (PA) and user’s accuracy (UA) values were higher than 95% when an April 1–May 15 time series was used. The PA and UA of cotton and spring maize were higher than 95% with image time series longer than April 1–August 15. As spring maize and cotton mature in late August and September–October, respectively, these two crops can be accurately mapped 4–6 weeks before harvest. In addition, summer maize could be accurately identified after August 15, more than one month before harvest. This study shows the potential of IAIN classifier for dealing with irregular time series and Sentinel-1 and Sentinel-2 image time series at early-season crop type mapping, which is useful for crop management.

Habitat mapping and change assessment of coastal wetlands by using Sentinel-2 time series and ecological expert knowledge

2020 ◽  
Author(s):  
Maria Adamo ◽  
Valeria Tomaselli ◽  
Francesca Mantino ◽  
Cristina Tarantino ◽  
Palma Blonda
Keyword(s):  
Time Series ◽  
Land Cover ◽  
Coastal Wetlands ◽  
Expert Knowledge ◽  
Land Reclamation ◽  
Habitat Mapping ◽  
The Mediterranean ◽  
The Impact ◽  
Sentinel 2

&lt;p&gt;Coastal wetlands are one of the most threatened ecosystems worldwide. In the Mediterranean Region, wetlands are undergoing rapid changes due to the increasing of human pressures (e.g. land reclamation, water resources exploitation) and climate changes (e.g. coastal erosion), with a resulting habitat degradation, fragmentation, and biodiversity loss.&lt;/p&gt;&lt;p&gt;Long-term habitat mapping and change detection are essential for the management of coastal wetlands as well as for evaluating the impact of conservation policies.&lt;/p&gt;&lt;p&gt;Earth observation (EO) data and techniques are a valuable resource for long-term habitat mapping, thanks to the large amount of available data and their high spatial and temporal resolution. In this study, we propose an approach based on the integration of time series of Sentinel-2 images and ecological expert knowledge for land cover (LC) mapping and automatic translation to habitats in coastal wetlands. In particular, the research relies on the exploitation of ecological rules based on combined information related to plant phenology, water seasonality of aquatic species, pattern zonation, and habitat geometric properties.&lt;/p&gt;&lt;p&gt;The methodology is applied to two Natura2000 sites, &amp;#8220;Zone umide della Capitanata&amp;#8221; and &amp;#8220;Paludi presso il Golfo di Manfredonia&amp;#8221;, located in the northeastern part of the Puglia region. These two areas are the most extensive wetlands of the Italian peninsula and the largest components of the Mediterranean wetland system.&lt;/p&gt;&lt;p&gt;Land Cover classes are labelled according to the FAO-LCCS taxonomy, which offers a framework to integrate EO data with in situ and ancillary data. Output habitat classes are labelled according to EUNIS habitat classification.&lt;/p&gt;

Sign in / Sign up

Export Citation Format

Share Document