NSFC Key Program 2026 @ NBU

Time is tight and the task is demanding. Let's all work together to accomplish this challenging mission! With full effort and unity, this is a vital opportunity for our team to shine. Step by step, with determination and cooperation, we can overcome any obstacle and achieve great success. Let's embrace this challenge with positive energy and mutual support-together, we will make it happen and create something truly remarkable!

Solar Data

Causal Inference

It is highly recommended to read the review article Causal Inference Meets Deep Learning: A Comprehensive Survey by Jiao et al. and the textbook Causal Inference & Machine Learning by Guo et al. . We also suggest watching the video An Introduction to Causal Inference in One Hour. Additionally, in line with the syllabus of the course Causality taught by Dr. Christina Heinze-Deml, the primary required textbooks and articles are those by Freedman et al \(^{1}\), Shalizi \(^{2}\), Maathuis et al \(^{3}\), Cinelli et al \(^{4}\), Peters et al \(^{5}\) and Shimizu \(^{6}\). A complete collection of these materials (including notes and slides) is available here. The main topics covered, together with their corresponding references, are listed below:

Introduction: Ch. 1 - 2 \(^{1}\)
Graphical models: Ch. 18.2 - 18.3.1 \(^{2}\)
Causal graphical models: Ch. 15.1 - 15.3 \(^{3}\)
Causal models: Ch. 20.1-20.2 \(^{2}\)
Covariate adjustment: Ch. 20.3-20.3.1 \(^{2}\) & Art. \(^{4}\)
Frontdoor criterion, instrumental variables and transportability: Ch. 20.3.2-20.3.4; 21.2 \(^{2}\)
Counterfactuals, potential outcomes and estimation: Ch. 21.1.3-21.1.5 \(^{2}\) & Ch. 3.3, 6.4, 6.9 \(^{5}\)
Towards structure learning: Ch. 8.2.1, 6.5, 7.2.1 \(^{5}\)
Constraint-based causal structure learning: Ch. 22 \(^{2}\) & 7.2.1 \(^{5}\)
Score-based causal structure learning and restricted SEMs: Ch. 4.1.1 - 4.1.4, 4.2.1, 7.2.2 \(^{5}\)
LiNGAM and Invariant causal prediction: Ch. 7.1-7.2 \(^{5}\) & Art. \(^{6}\)

Reading Group

The reading group runs for 5 weeks from November 26 to December 26, 2025, every Wednesday and Friday from 12:30 to 13:30. Topics 1, 2, 3, 9, and 11 will be presented by Yao; Topics 4 and 10 by Tianyuan; Topics 5 and 7 by Sixuan; and Topics 6 and 8 by Xinze. The details are as follows:

Week 1 Wed: Topics 1 & 2, Fri: Topic 3
Week 2 Wed: Topic 4, Fri: Topic 5
Week 3 Wed: Topic 6, Fri: Topic 7
Week 4 Wed: Topic 8, Fri: Topic 9
Week 5 Wed: Topic 10, Fri: Topic 11

Scientific Problem

We strongly encourage all team members to read the insightful grant proposal by Prof. Xu.

Mathematical Models
Deep Learning-Based Solutions
Physical Explanation