Comparison of simulated hyperspectral HyspIRI and multispectral Landsat 8 and Sentinel-2 imagery for multi-seasonal, regional land-cover mapping

2017 ◽  
Vol 200 ◽  
pp. 311-325 ◽  
Author(s):  
Matthew L. Clark
2019 ◽  
Vol 11 (3) ◽  
pp. 288 ◽  
Author(s):  
Luis Carrasco ◽  
Aneurin O’Neil ◽  
R. Morton ◽  
Clare Rowland

Land cover mapping of large areas is challenging due to the significant volume of satellite data to acquire and process, as well as the lack of spatial continuity due to cloud cover. Temporal aggregation—the use of metrics (i.e., mean or median) derived from satellite data over a period of time—is an approach that benefits from recent increases in the frequency of free satellite data acquisition and cloud-computing power. This enables the efficient use of multi-temporal data and the exploitation of cloud-gap filling techniques for land cover mapping. Here, we provide the first formal comparison of the accuracy between land cover maps created with temporal aggregation of Sentinel-1 (S1), Sentinel-2 (S2), and Landsat-8 (L8) data from one-year and test whether this method matches the accuracy of traditional approaches. Thirty-two datasets were created for Wales by applying automated cloud-masking and temporally aggregating data over different time intervals, using Google Earth Engine. Manually processed S2 data was used for comparison using a traditional two-date composite approach. Supervised classifications were created, and their accuracy was assessed using field-based data. Temporal aggregation only matched the accuracy of the traditional two-date composite approach (77.9%) when an optimal combination of optical and radar data was used (76.5%). Combined datasets (S1, S2 or S1, S2, and L8) outperformed single-sensor datasets, while datasets based on spectral indices obtained the lowest levels of accuracy. The analysis of cloud cover showed that to ensure at least one cloud-free pixel per time interval, a maximum of two intervals per year for temporal aggregation were possible with L8, while three or four intervals could be used for S2. This study demonstrates that temporal aggregation is a promising tool for integrating large amounts of data in an efficient way and that it can compensate for the lower quality of automatic image selection and cloud masking. It also shows that combining data from different sensors can improve classification accuracy. However, this study highlights the need for identifying optimal combinations of satellite data and aggregation parameters in order to match the accuracy of manually selected and processed image composites.


Author(s):  
I. D. Sanches ◽  
R. Q. Feitosa ◽  
P. Achanccaray ◽  
B. Montibeller ◽  
A. J. B. Luiz ◽  
...  

<p><strong>Abstract.</strong> The monitoring of agricultural activities at a regular basis is crucial to assure that the food production meets the world population demands, which is increasing yearly. Such information can be derived from remote sensing data. In spite of topic’s relevance, not enough efforts have been invested to exploit modern pattern recognition and machine learning methods for agricultural land-cover mapping from multi-temporal, multi-sensor earth observation data. Furthermore, only a small proportion of the works published on this topic relates to tropical/subtropical regions, where crop dynamics is more complicated and difficult to model than in temperate regions. A major hindrance has been the lack of accurate public databases for the comparison of different classification methods. In this context, the aim of the present paper is to share a multi-temporal and multi-sensor benchmark database that can be used by the remote sensing community for agricultural land-cover mapping. Information about crops in situ was collected in Luís Eduardo Magalhães (LEM) municipality, which is an important Brazilian agricultural area, to create field reference data including information about first and second crop harvests. Moreover, a series of remote sensing images was acquired and pre-processed, from both active and passive orbital sensors (Sentinel-1, Sentinel-2/MSI, Landsat-8/OLI), correspondent to the LEM area, along the development of the main annual crops. In this paper, we describe the LEM database (crop field boundaries, land use reference data and pre-processed images) and present the results of an experiment conducted using the Sentinel-1 and Sentinel-2 data.</p>


2017 ◽  
Vol 55 (3) ◽  
pp. 331-354 ◽  
Author(s):  
Gerald Forkuor ◽  
Kangbeni Dimobe ◽  
Idriss Serme ◽  
Jerome Ebagnerin Tondoh

2021 ◽  
pp. 70-77
Author(s):  
Т.К. МУЗЫЧЕНКО ◽  
М.Н. МАСЛОВА

В статье рассмотрено пространственное распределение типов земель в пределах трансграничного бассейна р. Раздольная. На основе дешифрирования космических снимков Sentinel-2 и Landsat 8 составлена карта пространственного распределения типов земель по состоянию на 2019 г. Исходя из геоэкологической классификации ландшафтов В.А. Николаева в данной работе было выделено 12 типов земель: используемые и неиспользуемые сельскохозяйственные земли, используемые и неиспользуемые рисовые поля, карьеры, леса, лесопосадки, рубки, луга, застроенные земли, водные объекты, а также кустарники и редколесья. Представлены абсолютные и относительные площади для каждого типа земель по трансграничному бассейну в целом, а также отдельно для его российской и китайской частей. По результатам дешифрирования данных дистанционного зондирования установлено, что российская и китайская части бассейна р. Раздольная имеют существенные трансграничные различия в структуре земель. На российской части бассейна лесами покрыто чуть более половины площади, но при этом значительные площади занимают сельскохозяйственные земли и луга. В некоторых местах луга и сельскохозяйственные земли преобладают в большей степени, чем леса. На китайской части лесные территории доминируют над другими типами земель. Сельскохозяйственные земли и луга образуют узкие и длинные полосы и имеют более мозаичное распространение, чем на российской части. Здесь заметно меньше площади застроенных земель, а площади рубок и лесопосадок больше, чем на российской части. Площади карьеров примерно равны в обеих частях бассейна. The transboundary Razdolnaya river basin is nearly evenly split up between Primorsky Krai of Russian Federation and Heilongjiang and Jilin provinces of People’s Republic of China. The Chinese and the Russian parts of the transboundary river have developed independently of each other. Therefore, the two have a different land cover and land use structure. The analysis of land cover and land use structure is of utmost importance for the understanding the modern state of land development and the possibilities of its future development. Using the remote sensing data, such as Sentinel-2 and Landsat 8 satellite imagery, the land cover and land use map of the Razdolnaya transboundary river basin for 2019 has been composed by means of the ArcMap 10.5 software package. According to V.A. Nikolaev’s geoecological classification of landscapes, we have identified 12 land types: forests, meadows, shrubs and woodlands, agricultural lands, unused agricultural lands, rice fields, unused rice fields, built-up areas, reforestation lands, logging, quarries, and bodies of water. We have provided area coverage for each type of land of the whole transboundary basin, and for the Russian and Chinese parts. According to the results of computer-aided visual deciphering and automatic deciphering, forests are the most common land use type in the basin. In the Chinese part of the basin, forests dominate over the other types of land. Agricultural lands and meadows have assumed narrow and linear shapes. Built-up areas have less coverage here than in the Russian part of the basin. However, the coverage of logging and reforestation lands is considerably larger than in the Russian part of the basin. In the Russian part of the basin, forests co-dominate with the agricultural lands and meadows. In some areas of this part of the basin forests disappear almost completely. The Russian part of the basin also has the larger coverage of shrubs and woodlands, unused agricultural lands, rice fields and unused rice fields. The coverage of quarries is roughly equal in both parts of the basin.


Author(s):  
Trinh Le Hung

The classification of urban land cover/land use is a difficult task due to the complexity in the structure of the urban surface. This paper presents the method of combining of Sentinel 2 MSI and Landsat 8 multi-resolution satellite image data for urban bare land classification based on NDBaI index. Two images of Sentinel 2 and Landsat 8 acquired closely together, were used to calculate the NDBaI index, in which sortware infrared band (band 11) of Sentinel 2 MSI image and thermal infrared band (band 10) of Landsat 8 image were used to improve the spatial resolution of NDBaI index. The results obtained from two experimental areas showed that, the total accuracy of classifying bare land from the NDBaI index which calculated by the proposed method increased by about 6% compared to the method using the NDBaI index, which is calculated using only Landsat 8 data. The results obtained in this study contribute to improving the efficiency of using free remote sensing data in urban land cover/land use classification.


2016 ◽  
Author(s):  
Dainis Jakovels ◽  
Jevgenijs Filipovs ◽  
Agris Brauns ◽  
Juris Taskovs ◽  
Gatis Erins

Sign in / Sign up

Export Citation Format

Share Document