Monitoring Forest Dynamics in the Andean Amazon: The Applicability of Breakpoint Detection Methods Using Landsat Time-Series and Genetic Algorithms

Abstract

Abstract:The Andean Amazon is an endangered biodiversity hot spot but its forest dynamics are less studied than those of the Amazon lowland and forests from middle or high latitudes. This is because its landscape variability, complex topography and cloudy conditions constitute a challenging environment for any remote-sensing assessment. Breakpoint detection with Landsat time-series data is an established robust approach for monitoring forest dynamics around the globe but has not been properly evaluated for implementation in the Andean Amazon. We analyzed breakpoint detection-generated forest dynamics in order to determine its limitations when applied to three different study areas located along an altitude gradient in the Andean Amazon in Ecuador. Using all available Landsat imagery for the period 1997-2016, we evaluated different pre-processing approaches, noise reduction techniques, and breakpoint detection algorithms. These procedures were integrated into a complex function called the processing chain generator. Calibration was not straightforward since it required us to define values for 24 parameters. To solve this problem, we implemented a novel approach using genetic algorithms. We calibrated the processing chain generator by applying a stratified training sampling and a reference dataset based on high resolution imagery. After the best calibration solution was found and the processing chain generator executed, we assessed accuracy and found that data gaps, inaccurate co-registration, radiometric variability in sensor calibration, unmasked cloud, and shadows can drastically affect the results, compromising the application of breakpoint detection in mountainous areas of the Andean Amazon. Moreover, since breakpoint detection analysis of landscape variability in the Andean Amazon requires a unique calibration of algorithms, the time required to optimize analysis could complicate its proper implementation and undermine its application for large-scale projects. In exceptional cases when data quality and quantity were adequate, we recommend the pre-processing approaches, noise reduction algorithms and breakpoint detection algorithms procedures that can enhance results. Finally, we include recommendations for achieving a faster and more accurate calibration of complex functions applied to remote sensing using genetic algorithms.

Automatic Mapping of Burned Areas Using Landsat 8 Time-Series Images in Google Earth Engine: A Case Study from Iran

“…Implementation of the feature selection algorithms in the Google Colab platform, which are divided into the wrapper and filter methods, can recognize and eliminate unrelated and redundant features and reduce the model complexity. For instance, Stromann et al (2020) [29], Cai et al (2018) [68], and Pal and Foody (2010) [69] reported the promising potential of wrapper methods, such as GA [64,[70][71][72][73][74], for finding the most-probable solutions without exploring the entire search space [36].…”

The Resilient Recurrent Behavior of Mediterranean Semi-Arid Complex Adaptive Landscapes

“…Trend analyses of multiyear satellite images allow the capture of gradual LDD processes [74], but they are not independent from constraining assumptions like linearity. Trend analyses were routinely employed for LDD assessment using coarse-and multi-temporal imagery [75].…”

Monitoring long-term forest dynamics with scarce data: a multi-date classification implementation in the Ecuadorian Amazon

“…Overall, our multi-date classification implementation was demonstrated to be far less sensitive to data scarcity and atmospheric contamination than other approaches using automated time-series analysis algorithms (Santos et al, 2017).…”

“…This results in time series with poor signal-to-noise ratio, as useful information about forest status is weak and not significant to differentiate from random noise. This is a limitation for transferring these novel algorithms to datascarce regions, such as the Tropical Andes (Santos, Dubovyk, & Menz, 2017), as time series analyses require rather dense data stacks over time.…”