Recent advances in processing remote sensing data have provided unprecedented potential for monitoring land covers. However, it is extremely challenging to deploy an automated monitoring system for different regions and across different years given the involved data heterogeneity over space and over time. The heterogeneity exists on two aspects. First, for many land covers, the distinguishing temporal patterns are only visible in certain discriminative period. Due to the change of weather conditions, the discriminative period can shift across space and time, which causes heterogeneity to the sequential data. Second, the collected remote sensing data are affected by acquisition devices and natural variables, e.g., precipitation and sunlight. In this paper, we introduce a novel framework to effectively detect land covers using the sequential remote sensing data. At the same time, we propose new learning strategies based on attention networks and domain adaptation to addresses the aforementioned challenges. The evaluation on two real-world applications- cropland mapping and burned area detection, demonstrate that the proposed method can effectively detect land covers under different weather conditions.
|Original language||English (US)|
|Title of host publication||SIAM International Conference on Data Mining, SDM 2019|
|Publisher||Society for Industrial and Applied Mathematics Publications|
|Number of pages||9|
|State||Published - 2019|
|Event||19th SIAM International Conference on Data Mining, SDM 2019 - Calgary, Canada|
Duration: May 2 2019 → May 4 2019
|Name||SIAM International Conference on Data Mining, SDM 2019|
|Conference||19th SIAM International Conference on Data Mining, SDM 2019|
|Period||5/2/19 → 5/4/19|
Bibliographical noteFunding Information:
This work was funded by the NSF Awards 1029711 and DTC seed grant. Access to computing facilities was provided by Minnesota Supercomputing Institute.