Importance of the Collection of Abundant Ground‐Truth Data for Accurate Detection of Spatial and Temporal Variability of Vegetation by Satellite Remote Sensing

Increasing the Effectiveness of Active Learning: Introducing Artificial Data Generation in Active Learning for Land Use/Land Cover Classification

“…The technological development of air and spaceborne sensors and the increasing number of remote sensing missions have allowed the continuous collection of large amounts of high quality remotely sensed data. These data are often composed of multi-and hyperspectral satellite imagery, essential for numerous applications, such as Land Use/Land Cover (LULC) change detection, ecosystem management [1], agricultural management [2], water resource management [3], forest management, and urban monitoring [4]. Despite LULC maps being essential for most of these applications, their production is still a challenging task [5,6].…”

“…The development of a reliable automated method is still a challenge among the ML and remote sensing community, since the effectiveness of existing methods varies across applications and geographical areas [5]. Typically, this method requires the existence of ground-truth data, which are frequently outdated or nonexistent for the required time frame [1]. On the other hand, employing a ML method provides readily available and relatively inexpensive LULC maps.…”

Review: Monitoring of land cover changes and plant phenology by remote‐sensing in East Asia

“…In addition, the instruments are affordable for individual sites, but prohibitively expensive for large‐scale use because of the large number of instruments that would be required. Although satellite data include uncertainties caused by the heterogeneity of the plant species and vegetation cover within the satellite footprint (Nagai, Nasahara, Akitsu, et al, 2020), and the dataset may be reduced by cloud contamination, we should develop methods for the evaluation of leaf traits using daily‐resolution satellite data such as that provided by 500‐m‐resolution MODIS/Terra and Aqua satellites, which would support analyses at a global scale (see also Noda et al, 2021).…”

Impacts of environmental pollution on mangrove phenology: Combining remotely sensed data and generalized additive models

“…In this regard, there is no "one size fits all" index or algorithm and each case should be evaluated separately. The role of ground truth data to discern the most accurate satellite-based phenology reconstruction techniques is crucial (Nagai et al, 2020). Within this study, the absence of validation data constituted an important source of uncertainty, as it impeded comparisons between vegetation indices and smoothing algorithms.…”