Repositorio
Institucional

Somos-Valenzuela, Marcelo

Morales, Bastian

Garcia-Pedrero, Angel

Lizama, Elizabet

Lillo-Saavedra, Mario

Gonzalo-Martin, Consuelo

Chen, Ningsheng

Patagonian Andes Landslides Inventory: The Deep Learning's Way to Their Automatic Detection

MDPI

REMOTE SENSING

en

Landslide inventories are crucial to studying the dynamics, associated risks, and effects of these geomorphological processes on the evolution of mountainous landscapes. The production of landslide maps is mainly based on manual visual interpretation methods of aerial and satellite images combined with field surveys. In recent times, advances in machine learning methods have made it possible to explore new semi-automated landslide detection methodologies using remotely detected images. In this sense, developing new artificial intelligence models based on Deep Learning (DL) opens up an excellent opportunity to automate this arduous process. Although the Andes mountain range is one of the most geomorphologically active areas on the planet, the few investigations that use DL mainly focus on mountain ranges in Europe and Asia. One of the main reasons is the low density of landslide data available in the Andean areas, making it difficult to experiment with DL models requiring large data volumes. In this work, we seek to narrow the existing gap in the availability of landslide inventories in the area of the Patagonian Andes. In addition, the feasibility and efficiency of DL techniques are studied to develop landslide detection models in the Andes from the generated datasets. To achieve this goal, we generated in a manual process a datasets of 10,000 landslides for northern Chilean Patagonia (42-45 degrees S), being the largest freely accessible landslide datasets in this region. We implement a machine learning model, through DL, to detect landslides in optical images of the Sentinel-2 constellation using a model based on the DeepLabv3+ architecture, a state-of-the-art deep learning network for semantic segmentation. Our results indicate that the algorithm detects landslides with an accuracy of 0.75 at the object level. For its part, the segmentation reaches a precision of 0.86, a recall of 0.74, and an F1-score of 0.79. The correlation of the segmentation measured through the Matthews correlation coefficient shows a value of 0.59, and the geometric similarity of the correctly detected landslides measured through the Jaccard score reaches 0.70. Although the model shows a good response in the testing area, errors are generated that can be explained by geometric and spectral relationships, which should be solved through new training approaches and data sets.

artículo original

This research was funded by by the Chilean Science Council (ANID) through the Program of International Cooperation (PII-180008), Anillo (ACT210080), PATSER (ANID/R20F0002), and Water Research Center For Agriculture and Mining, CRHIAM (ANID/FONDAP/15130015).

Esta investigación fue financiada por el Consejo Científico de Chile (ANID) a través del Programa de Cooperación Internacional (PII-180008), Anillo (ACT210080), PATSER (ANID/R20F0002) y el Centro de Investigación del Agua para la Agricultura y Minería, CRHIAM (ANID/ FONDAP/15130015).

10.3390/rs14184622

PDF

landslide detection

deep learning

Sentinel-2

Patagonian Andes

Ciencias Ambientales

Geociencias

Multidisciplinaria

Sensores remotos

Ciencia de la imagen y tecnología fotográfica

detección de deslizamientos de tierra

aprendizaje profundo

Sentinel-2

Andes patagónicos

Geociencias

Ciencias de la Computación

Sensores Remotos

Patagonian Andes Landslides Inventory: The Deep Learning's Way to Their Automatic Detection

artículo original

version publicada

CC BY 4.0

CC BY 4.0

acceso abierto

acceso abierto

ANID-FONDAP 15130015

ANID PII-180008

ANID ACT210080

ANID R20F0002

ANID FONDAP 15130015

WOS:000856909400001