Depression is a leading cause of global disease burden, poor quality of life, disability and suicide, and commonly occurs in adolescence and early adulthood. Insomnia and circadian factors were regarded as potential targets for preventing worsening of depressive symptoms. Additionally, digital insomnia treatment reduces depressive symptoms but is insufficient for individuals with an evening chronotype. Circadian intervention is an adjunctive treatment for sleep disturbance and depression, but is often overlooked. In this study, we aim to evaluate the effect of guided digital insomnia and circadian intervention (dCBT-I + dCI) in reducing depressive symptoms in college students with insomnia and an evening chronotype compared with digital insomnia intervention alone (dCBT-I) and a health education group (dHE). We also aim to develop and evaluate multimodal prediction models to identify individuals who are more or less likely to respond to the interventions, using clinical, behavioral, circadian, and digital engagement data.