Developing Algorithms to Improve the Temporal Sampling of Satellite Data

March 24, 2023

Enhancing Temporal Resolution of Satellite Soil Moisture Data: Implications for Agriculture, Water Management, Climate Change Research, and Ecosystem Health

Enhancing the temporal repeat of satellite data for obtaining soil moisture information is a vital research area due to its far-reaching implications for various aspects of human life and the environment. The benefits of improving the temporal resolution of satellite data in these domains are manifold:


Soil moisture is a key parameter that influences crop growth, yield, and overall productivity. Timely and accurate soil moisture data enables farmers to make informed decisions regarding irrigation scheduling, crop selection, and disease management. This, in turn, can lead to better crop yields, reduced input costs, and sustainable agriculture practices. The increasing global demand for food security makes improving the temporal resolution of soil moisture data even more critical.

Water resource management:

Water scarcity is a pressing issue in many parts of the world. Enhanced temporal resolution of satellite soil moisture data can significantly improve the efficiency of water resource management by providing accurate and up-to-date information on water availability and soil water storage. This enables policymakers and water managers to make informed decisions about water allocation, conservation measures, and infrastructure planning, ultimately leading to more sustainable water use.

Climate change research:

Soil moisture plays a significant role in the Earth's energy and water cycles, which are essential components of the global climate system. High-quality, high-resolution soil moisture data can provide valuable insights into the interactions between the atmosphere, land surface, and vegetation, contributing to a better understanding of climate change processes. Moreover, these data sets can be used to calibrate and validate climate models, enhancing their predictive capabilities and enabling more accurate projections of future climate scenarios.

Ecosystem health:

Soil moisture has a strong influence on the health and functioning of ecosystems. It affects plant growth, species distribution, nutrient cycling, and overall biodiversity. By improving the temporal resolution of satellite soil moisture data, researchers can gain a deeper understanding of ecosystem dynamics and how they respond to environmental changes, such as climate change or land use modifications. This knowledge can be used to guide conservation efforts and develop adaptive management strategies to protect and restore ecosystems.

Disaster risk reduction:

Timely and accurate soil moisture data can contribute to early warning systems for droughts, floods, and landslides. Improved temporal resolution allows for better monitoring and prediction of these natural disasters, helping to minimize their impacts on human lives and property. In addition, the data can be used to inform land-use planning, disaster preparedness, and post-disaster recovery efforts.

We are developing novel algorithms and approaches to obtain more frequent soil moisture data from space by utilizing a new satellite system, such as NASA's cyclone-tracking satellite called CYGNSS.

(left) Soil moisture data from a new satellite system (right) soil moisture data from the previous satellite system (SMAP)

What we aim to achieve

We aim to improve the temporal repeat of soil moisture data from space to obtain more accurate and timely information for enhanced decision-making in agriculture, water management, and environmental monitoring. This increased precision can lead to better resource management, increased productivity, and a deeper understanding of the Earth's climate and ecosystems.

We enhance soil moisture estimates by employing multi-sensor data fusion, which combines data from various satellite missions and sensors, using techniques like data assimilation and machine learning to leverage the strengths of each sensor for a comprehensive and accurate product. We also develop and refine advanced algorithms, including statistical methods and physically-based approaches, to account for factors like land cover, vegetation, and soil properties. Additionally, incorporating satellite-derived soil moisture data into hydrological and land surface models through data assimilation techniques, such as Kalman filtering and ensemble-based methods, helps improve the representation of soil moisture and the accuracy of model predictions.

Data and analytic skills we use for this project

  • Multi-sensor data fusion: Integrating data from diverse satellite missions and sensors to create improved soil moisture estimates.
  • Data assimilation techniques: Employing methods like machine learning to merge datasets, capitalizing on the strengths of each sensor for a comprehensive and accurate product.
  • Advanced algorithm development: Creating and refining algorithms using statistical methods, machine learning, and physically-based approaches to retrieve soil moisture from remote sensing data.
  • Hydrological model integration: Incorporating satellite-derived soil moisture data into hydrological and land surface models using data assimilation techniques, such as Kalman filtering and ensemble-based methods, for more accurate soil moisture information.
This project aims not only to improve the temporal repeat of the satellite-based soil moisture data but also to explore other related research topics below. If you are interested in any of the following research areas, please do not hesitate to contact me!
  1. Deep learning-based multi-sensor data fusion: Investigating the application of advanced deep learning techniques for integrating soil moisture data from various satellite sensors and missions.
  2. Uncertainty quantification and propagation: Analyzing the uncertainties in satellite-derived soil moisture products, and understanding how they propagate through various processing steps, algorithms, and data fusion techniques.
  3. Soil moisture retrieval in complex environments: Developing innovative methods for accurately estimating soil moisture in challenging environments, such as urban areas, mountainous regions, and areas with dense vegetation cover.
  4. Data assimilation for improved drought and flood prediction: Investigating the effectiveness of assimilating satellite-derived soil moisture data into hydrological and land surface models for better prediction of drought and flood events.
  5. Satellite-derived soil moisture and agricultural productivity: Examining the relationship between satellite-based soil moisture measurements and agricultural productivity, focusing on the potential for data-driven decision support tools for farmers.
  6. Integration of satellite and ground-based data for improved soil moisture monitoring: Evaluating the benefits of combining satellite-derived soil moisture data with ground-based measurements from sensor networks, in terms of accuracy, reliability, and spatiotemporal coverage.
  7. Impact of climate change on soil moisture dynamics: Assessing the influence of climate change on soil moisture patterns and their implications for water resources, agriculture, and ecosystems.


Read other projects

Harnessing Deep Learning to Predict and Decode the Mysteries of Flash Droughts (GAN/SHAP/3D-CNN with Transfer Learning)

The application of deep learning in predicting flash droughts offers a transformative approach to understanding and anticipating these rapid-onset events, significantly enhancing preparedness and response strategies. By unraveling the complex mechanisms behind flash droughts, this project aims to provide precise, timely forecasts, thereby mitigating the severe agricultural, ecological, and socioeconomic impacts associated with these phenomena.

Read this project
Streamflow and Drought Predictions over Ungaged Regions using Deep and Transfer Learning Approaches

Streamflow and flash drought predictions are essential for managing water resources and mitigating potential disasters in ungaged regions. With remotely-sensed data, deep and transfer learning approaches provide powerful tools to analyze complex hydrological data, enabling more accurate predictions and better decision-making in these areas.

Read this project
Applications of Bayesian Machine Learning in Big Data in Earth Science

Bayesian methods help us improve our guesses by using new information. In Earth science, these methods are applied to big data to better understand our planet. This approach is useful for predicting things like natural disaster patterns and climate changes. By continuously updating our knowledge with new data, we can make more accurate predictions and decisions in Earth science.

Read this project
Water Balance Budgeting with Bayesian Machine Learning

The water balance equation in Earth science, P = E + R + etc, describes the relationship between precipitation (P), evaporation (E), runoff (R), and etc (e.g., soil moisture, ground water) in a given area. Bayesian inference can be applied to solve this equation by incorporating prior knowledge and updating the probability distributions of the variables based on new data, ultimately improving water resource management and prediction.

Read this project
Integrating Earth Science and Engineering for Climate Resilience: Innovative Approaches to Infrastructure and Societal Justice

Earth science informs infrastructure development by providing insights into site suitability, resource management, and sustainable design, enhancing the resilience and long-term viability of projects. It also plays a crucial role in addressing societal justice related to climate change by helping identify vulnerable communities and develop mitigation strategies, ensuring equitable access to resources and protection from environmental hazards.

Read this project
Enhancing Earth Science Predictions through Advanced Data Assimilation Techniques

Data assimilation is vital in earth science as it integrates diverse observations and model simulations, improving the accuracy of forecasts and predictions. This process enhances our understanding of complex Earth systems, enabling better decision-making for environmental management and climate adaptation.

Read this project
Floods and Droughts Predictions using Machine Learning Approaches

Satellite data and machine learning transformed Earth science by predicting and monitoring natural disasters. This combination delivers precise and timely predictions, crucial for mitigating the impacts of events like floods and droughts.

Read this project
Data Error Characterizations

Characterizing the error of satellite data and land surface models is vital in Earth science, as it ensures the accuracy and reliability of information used for monitoring and predicting environmental phenomena. By understanding these errors, scientists can refine data interpretation, enhance models, and ultimately make better-informed decisions about the Earth's complex systems.

Read this project
Developing Algorithms to Improve the Temporal Sampling of Satellite Data

Enhancing the temporal repeat of satellite data for obtaining soil moisture information is a vital research area due to its implications for agriculture, water resource management, climate change research, and ecosystem health. It helps in making informed decisions, increasing productivity, and reducing the impact of natural disasters, as well as contributing to our understanding of the global climate system.

Read this project
Exploring the Impact of Human Activities on the Subdaily Global Terrestrial Water Cycle

Humans have been modifying the Earth's surface for thousands of years, with practices like clearing forests for agriculture and creating uniform land covers. But how do these changes impact the subdaily global terrestrial water cycle? That's the question a project aims to answer.

Read this project
Satellite Image Disaggregation with Machine Learning

Microwave soil moisture data is critical for agriculture, weather, and climate modeling, but has low spatial resolution. Disaggregation via machine learning can improve resolution, offering detailed local soil moisture data. Machine learning can handle complex relationships between microwave signals and soil moisture.

Read this project