Sijie Zhao

Nanjing University M.S., Nanjing University (2025)

I am Sijie Zhao, I study at Nanjing University and work under the supervision of Prof.Xueliang Zhang and Prof.Pengfeng Xiao. My research field is AI4Earth, mainly including the fields of remote sensing and meteorology. My research interests mainly include Efficient Earth Data Representation, Universal Earth Foundation Model, and Black-box Model-based Scientific Discovery. Feel free to send me an email if you would like to chat with me for any reason.

Google Scholar GitHub Resume
Education
  • Nanjing University

    Nanjing University

    M.S. in School of Geography and Ocean Science (Supervised by Prof. Xueliang Zhang and Prof. Pengfeng Xiao) Sep. 2023 - Now

  • Nanjing University

    Nanjing University

    B.S. in School of Geography and Ocean Science Sep. 2019 - Jul. 2023

Honors & Awards
  • National Scholarship 2024
  • National Endeavor Scholarship 2022
  • Special Award in the 10th National College GIS Application Skills Competition 2021
Experience
  • Shanghai Artificial Intelligence Lab

    Shanghai Artificial Intelligence Lab

    Research Internship (Supervised by Dr. Hao Chen) Sep. 2023 - Now

  • AGIBot

    AGIBot

    Large vision model algorithm Internship Jun. 2023 - Sep. 2023

Service
News
2025
🔥 New preprint Temporal-Spectral-Spatial Unified Remote Sensing Dense Prediction is now available on arXiv.
May 20
🎉 The article titled VegeDiff: Latent Diffusion Model for Geospatial Vegetation Forecasting has been published in IEEE Transactions on Geoscience and Remote Sensing (TGRS, SCI Q1 TOP, IF=8.3).
Apr 23
🔥 New preprint Transforming Weather Data from Pixel to Latent Space is now available on arXiv.
Mar 20
Selected Publications (view all )
Temporal-Spectral-Spatial Unified Remote Sensing Dense Prediction
Temporal-Spectral-Spatial Unified Remote Sensing Dense Prediction

Sijie Zhao, Feng Liu, Xueliang Zhang†, Hao Chen†, Pengfeng Xiao, Lei Bai(† corresponding author)

arXiv 2025 Journal

This research introduces TSSUN, a novel deep learning model that unifies diverse remote sensing data and dense prediction tasks. It addresses data heterogeneity challenges by standardizing input/output, achieving state-of-the-art performance across various applications without task-specific modifications.

[Paper] [Code] [Cite]

Temporal-Spectral-Spatial Unified Remote Sensing Dense Prediction
Temporal-Spectral-Spatial Unified Remote Sensing Dense Prediction

Sijie Zhao, Feng Liu, Xueliang Zhang†, Hao Chen†, Pengfeng Xiao, Lei Bai(† corresponding author)

arXiv 2025 Journal

This research introduces TSSUN, a novel deep learning model that unifies diverse remote sensing data and dense prediction tasks. It addresses data heterogeneity challenges by standardizing input/output, achieving state-of-the-art performance across various applications without task-specific modifications.

[Paper] [Code] [Cite]

Transforming Weather Data from Pixel to Latent Space
Transforming Weather Data from Pixel to Latent Space

Sijie Zhao, Feng Liu, Xueliang Zhang†, Hao Chen†, Tao Han, Junchao Gong, Ran Tao, Pengfeng Xiao, Xinyu Gu, Lei Bai, Wanli Ouyang(† corresponding author)

arXiv 2025 Conference

This research introduces WLA, a novel deep learning model that compresses massive weather datasets into a compact latent space. This innovation significantly reduces data storage and computational costs, while improving the accuracy and adaptability of weather task models across diverse scenarios.

[Paper] [Code] [Cite]

Transforming Weather Data from Pixel to Latent Space
Transforming Weather Data from Pixel to Latent Space

Sijie Zhao, Feng Liu, Xueliang Zhang†, Hao Chen†, Tao Han, Junchao Gong, Ran Tao, Pengfeng Xiao, Xinyu Gu, Lei Bai, Wanli Ouyang(† corresponding author)

arXiv 2025 Conference

This research introduces WLA, a novel deep learning model that compresses massive weather datasets into a compact latent space. This innovation significantly reduces data storage and computational costs, while improving the accuracy and adaptability of weather task models across diverse scenarios.

[Paper] [Code] [Cite]

VegeDiff：Latent Diffusion Model for Geospatial Vegetation Forecasting
VegeDiff：Latent Diffusion Model for Geospatial Vegetation Forecasting

Sijie Zhao, Hao Chen†, Xueliang Zhang†, Pengfeng Xiao, Lei Bai, Wanli Ouyang(† corresponding author)

IEEE Transactions on Geoscience and Remote Sensing (TGRS, SCI Q1 TOP, IF=8.3) 2025 Journal

This research introduces VegeDiff to forecast future vegetation states by employing a novel diffusion model to probabilistically capture uncertainties in vegetation change. It accurately models dynamic meteorological and static environmental impacts, providing clear, precise predictions, outperforming existing deterministic methods.

[Paper] [Code] [Cite]

VegeDiff：Latent Diffusion Model for Geospatial Vegetation Forecasting
VegeDiff：Latent Diffusion Model for Geospatial Vegetation Forecasting

Sijie Zhao, Hao Chen†, Xueliang Zhang†, Pengfeng Xiao, Lei Bai, Wanli Ouyang(† corresponding author)

IEEE Transactions on Geoscience and Remote Sensing (TGRS, SCI Q1 TOP, IF=8.3) 2025 Journal

This research introduces VegeDiff to forecast future vegetation states by employing a novel diffusion model to probabilistically capture uncertainties in vegetation change. It accurately models dynamic meteorological and static environmental impacts, providing clear, precise predictions, outperforming existing deterministic methods.

[Paper] [Code] [Cite]

RS-Mamba for Large Remote Sensing Image Dense Prediction
RS-Mamba for Large Remote Sensing Image Dense Prediction

Sijie Zhao, Hao Chen†, Xueliang Zhang†, Pengfeng Xiao, Lei Bai, Wanli Ouyang(† corresponding author)

IEEE Transactions on Geoscience and Remote Sensing (TGRS, SCI Q1 TOP, IF=8.3) 2024 Journal

This research introduces Remote Sensing Mamba (RSM) to efficiently model global context in large remote sensing images. RSM overcomes the quadratic complexity of transformers by using an omnidirectional selective scan, achieving state-of-the-art dense prediction performance on VHR images.

[Paper] [Code] [Cite]

RS-Mamba for Large Remote Sensing Image Dense Prediction
RS-Mamba for Large Remote Sensing Image Dense Prediction

Sijie Zhao, Hao Chen†, Xueliang Zhang†, Pengfeng Xiao, Lei Bai, Wanli Ouyang(† corresponding author)

IEEE Transactions on Geoscience and Remote Sensing (TGRS, SCI Q1 TOP, IF=8.3) 2024 Journal

This research introduces Remote Sensing Mamba (RSM) to efficiently model global context in large remote sensing images. RSM overcomes the quadratic complexity of transformers by using an omnidirectional selective scan, achieving state-of-the-art dense prediction performance on VHR images.

[Paper] [Code] [Cite]

Exchanging dual-encoder–decoder：A new strategy for change detection with semantic guidance and spatial localization
Exchanging dual-encoder–decoder：A new strategy for change detection with semantic guidance and spatial localization

Sijie Zhao, Hao Chen†, Xueliang Zhang†, Pengfeng Xiao(† corresponding author)

IEEE Transactions on Geoscience and Remote Sensing (TGRS, SCI Q1 TOP, IF=8.3) 2023 Journal

This research introduces a novel exchanging dual encoder-decoder structure for binary change detection. It addresses limitations of existing methods by fusing bitemporal features at the decision level and leveraging bitemporal semantic features. The proposed model achieves superior performance and high efficiency across various change detection scenarios.

[Paper] [Code] [Cite]

Exchanging dual-encoder–decoder：A new strategy for change detection with semantic guidance and spatial localization
Exchanging dual-encoder–decoder：A new strategy for change detection with semantic guidance and spatial localization

Sijie Zhao, Hao Chen†, Xueliang Zhang†, Pengfeng Xiao(† corresponding author)

IEEE Transactions on Geoscience and Remote Sensing (TGRS, SCI Q1 TOP, IF=8.3) 2023 Journal

This research introduces a novel exchanging dual encoder-decoder structure for binary change detection. It addresses limitations of existing methods by fusing bitemporal features at the decision level and leveraging bitemporal semantic features. The proposed model achieves superior performance and high efficiency across various change detection scenarios.

[Paper] [Code] [Cite]

All publications