Showing papers in "Remote Sensing of Environment in 2020"

TL;DR: The potential of DL in environmental remote sensing, including land cover mapping, environmental parameter retrieval, data fusion and downscaling, and information reconstruction and prediction, will be analyzed and a typical network structure will be introduced.

TL;DR: In this paper, the authors present the agronomical variables and plant traits that can be estimated by remote sensing, and describe the empirical and deterministic approaches to retrieve them, and provide a synthesis of the emerging opportunities that should strengthen the role of remote sensing in providing operational, efficient and long-term services for agricultural applications.

TL;DR: Wang et al. as mentioned in this paper used the full archive of 30-m resolution Landsat images on the Google Earth Engine platform to map the Global Artificial Impervious Areas (GAIA) from 1985 to 2018.

TL;DR: In this article, the authors outline the historical development of night-time optical sensors up to the current state-of-the-art sensors, highlight various applications of night light data, discuss the special challenges associated with remote sensing of night lights with a focus on the limitations of current sensors, and provide an outlook for the future of remote sensing.

TL;DR: It is indicated that multimodal data fusion using low-cost UAV within a DNN framework can provide a relatively accurate and robust estimation of crop yield, and deliver valuable insight for high-throughput phenotyping and crop field management with high spatial precision.

TL;DR: In this article, a pseudo-labeling and sample selection scheme was proposed to improve the transferability of deep CNNs for land cover classification with high-resolution and heterogeneous remote sensing images.

TL;DR: A detailed review of existing methods for phenology detection and emerging new techniques based on the analysis of time-series, multispectral remote sensing imagery is presented in this paper.

TL;DR: The development of applications like lidR are of fundamental importance for developing transparent, flexible and open ALS tools to ensure not only reproducible workflows, but also to offer researchers the creative space required for the progress and development of the discipline.

TL;DR: The Integrated Multi-satellitE Retrievals for Global Precipitation Measurement (IMERG) produces the latest generation of satellite precipitation estimates and has been widely used since its release in 2014 as mentioned in this paper.

TL;DR: In this article, it is shown that all of the arguments put forward for the use of the kappa coefficient in accuracy assessment are flawed and/or irrelevant as they apply equally to other, sometimes easier to calculate, measures of accuracy.

TL;DR: In this paper, a machine-learning model, the Mixture Density Network (MDN), was proposed for consistent, cross-mission retrievals of near-surface concentration of chlorophyll-a (Chla) in various aquatic ecosystems with broad ranges of trophic levels.

TL;DR: In this paper, a land surface phenology (LSP) algorithm is proposed to estimate the timing of phenophase transitions and quantify the nature and magnitude of seasonality in remotely sensed land surface conditions.

TL;DR: In this article, the authors provide an interdisciplinary focus to explore current developments in terrestrial laser scanning (TLS) to measure and monitor forest structure, and argue that TLS data will play a critical role in understanding fundamental ecological questions about tree size and shape, allometric scaling, metabolic function and plasticity of form.

TL;DR: In this paper, the authors classified land and water in all 3.4 million Landsat 5, 7, and 8 scenes from 1999 to 2018 and performed a time-series analysis to produce maps that characterize inter-annual and intra-ANNual open surface water dynamics.

TL;DR: In this paper, the authors presented an algorithm that exploits all available Sentinel-1 SAR images in combination with historical Landsat and other auxiliary data sources hosted on the Google Earth Engine (GEE) to rapidly map surface inundation during flood events.

TL;DR: In this paper, the relationship between SIF and gross primary productivity (GPP) at the canopy scale was investigated and the dominant role of canopy structure in the SIF-GPP relationship was demonstrated.

TL;DR: In the proposed method, a deep convolutional neural network is designed to extract and fuse in-depth spectral and local spatial features, and the conditional random field (CRF) model further incorporates the spatial-contextual information to improve the problem of holes and isolated regions in the classification map.

TL;DR: In this article, the authors present a community effort to develop good practice guidelines for the validation of global coarse-scale satellite soil moisture products and provide theoretical background, a review of state-of-the-art methodologies for estimating errors in soil moisture data sets, practical recommendations on data pre-processing and presentation of statistical results, and a recommended validation protocol that is supplemented with an example validation exercise focused on microwave-based surface soil moisture product.

TL;DR: In this article, a system is presented that uses time series of Landsat data and spectral mixture analysis to detect both degradation and deforestation in forested landscapes, which are transformed into spectral endmember fractions and are used to calculate the Normalized Degradation Fraction Index (NDFI).

TL;DR: Wang et al. as mentioned in this paper developed a straightforward and efficient pixel-and phenology-based algorithm to generate annual cropping intensity maps over large spatial domains at high spatial resolution by integrating Landsat-8 and Sentinel-2 time series image data for 2016-2018 using the Google Earth Engine (GEE) platform.

TL;DR: This study recommends exploiting the estimation of nitrogen via the proxy of proteins using hyperspectral data and in particular the short-wave infrared (SWIR) spectral domain, which represents an interesting perspective for future research in view of new spaceborne imaging spectroscopy sensors.

TL;DR: In this paper, the authors compared reflectance and fractional cover candidate severity indices derived from Sentinel 2 satellite imagery using a random forest (RF) machine learning framework, and the results indicate that fire severity can be mapped with very high accuracy using Sentinel 2 imagery and RF supervised classification.

TL;DR: In this article, the authors presented a hybrid approach that combines MODIS highest resolution (250m) near-infrared band and active fire information from thermal channels, which was used to obtain a time series of global burned area dataset (named FireCCI51), covering the 2001-2018 period.

TL;DR: A new algorithm for COntinuous monitoring of Land Disturbance (COLD) using Landsat time series, which can detect many kinds of land disturbance continuously as new images are collected and provide historical land disturbance maps retrospectively is developed.

TL;DR: In this article, a comparison of three NASA missions (GEDI, ICESat-2 and NISAR) over Sonoma county in California, USA is presented.

TL;DR: The interannual dynamics of coastal tidal flats area in China over the last three decades can be divided into three periods: a stable period during 1986-1992, an increasing period during 1993-2001 and a decreasing period during 2002-2016.

TL;DR: Initial performance testing of OLI-2 and TIRS-2 indicate that the instruments are of excellent quality and expected to match or improve on Landsat 8 data quality.

TL;DR: In this paper, a machine learning approach termed the extreme gradient boosting tree (BST) was employed to develop an algorithm for Chla estimation from satellite-borne sensors in turbid lakes.

TL;DR: In this article, the authors provide a 50-year retrospective of the developments in the field in terms of both instrumentation and methods and also show that spectral features characteristic of the main benthic groups in shallow water are consistent from the tropics to sub-arctic regions and from salty to freshwaters.

TL;DR: In this paper, a new vegetation index was derived from dual-pol (DpRVI) SAR data for canola, soybean, and wheat, over a test site in Canada.