| AUTOMATIC CORN AND SOYBEAN MAPPING BASED ON DEEP LEARNING METHODS (CASE STUDY: HAMILTON, HARDIN, BOONE, STORY, DALLAS, POLK, AND JUSPER COUNTIES IN LOWA STATE) |
| Paper ID : 1011-GEOSPATIAL (R3) |
| Authors: |
|
Mahdieh Fathi, Reza Shah-Hosseini * School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, Tehran, Iran |
| Abstract: |
| Corn and Soybean are important crops for the world’s people. Monitoring and mapping corn and soybean fields play an important role in agricultural planning and monitoring. Nowadays, intelligent management of corn and soybean fields has improved by remote sensing technology and deep learning algorithms. These research aims are a comparative study on deep learning models such as 1-D CNN, 1-D CNN-LSTM, and 2-D U-net by using extracted multi-temporal maps of NDVI index from Landsat-8 images for separation of corn and soybean fields from other crop fields (due to the NDVI curve similarity of soybean and corn fields) in the united states, in 2020. The results showed that the 2-D U-net model performed best with Kappa coefficient (88.48 and 88.89) and accuracy (94.31 and 95.64) for corn and soybean classes (respectively) due to the identification of complex features from the NDVI multi-temporal index of months March to November in the united states. |
| Keywords: |
| Corn, Soybean, Landsat-8, NDVI, multi-temporal, Deep Learning |
| Status : Paper Accepted (Poster Presentation) |
