<p dir="ltr">This study aims to develop Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), and Transformer-based Informer models and evaluate the performance of these models using data from one, two, three, and four weeks in advance to predict the progression of rice leaf blast disease; and assess the generalizability of these models across various climatic regions in Taiwan. This research utilized multi-location rice leaf blast diseased leaf percentage data collected between 2015 and 2021 in Taiwan, along with weather data from the Taiwanese meteorological observation network to predict rice blast disease one week in advance, serving as a benchmark for comparing with predictions made two, three, and four weeks in advance.</p>
| Identifer | oai:union.ndltd.org:purdue.edu/oai:figshare.com:article/26367148 |
| Date | 28 July 2024 |
| Creators | Shih Yun Lin (19208476) |
| Source Sets | Purdue University |
| Detected Language | English |
| Type | Text, Thesis |
| Rights | CC BY 4.0 |
| Relation | https://figshare.com/articles/thesis/_b_A_COMPARATIVE_EVALUATION_OF_LONG_SHORT-TERM_MEMORY_LSTM_GATED_RECURRENT_UNITS_GRU_AND_TRANSFORMER-BASED_INFORMER_MODEL_FOR_PREDICTING_RICE_LEAF_BLAST_b_/26367148 |
Page generated in 0.0018 seconds