Tracking the impact of typhoons on maize growth and recovery using Sentinel-1 and Sentinel-2 data: A case study of Northeast China

•Remote sensing parameters using time series analysis: by employing time series analysis on Sentinel data, a comprehensive exploration of spectral and polarization responses was conducted, revealing correlations with maize damage severity.•Model for maize damage assessment: a model was developed using the Random Forest algorithm to monitor maize damage severity in different post-typhoon periods, generating maps depicting the distribution and magnitude of maize damage with improved monitoring accuracy.•Maize damage recovery from post-typhoons until maturity period: the study also assessed the recovery of maize damage during the period from typhoons to harvest, providing insights into the resilience and recovery trajectory of maize following severe typhoon events.•SAR and optical data fusion: the study highlighted the importance of SAR and optical data fusion in elucidating the dynamics of crop losses caused by typhoons, providing essential insights for proactive disaster risk reduction strategies in agriculture.•Post-typhoon maize damage impact factors: analysis of terrain and meteorological data revealed that post-typhoon maize disasters primarily occurred in low-lying and flat areas, with meteorological factors such as maximum wind speed and daily cumulative precipitation significantly impacting damage severity. The increasing frequency of typhoon events, attributed to global climate change, has significantly affected agricultural production, predominantly resulting in substantial negative consequences. Accurate and timely assessment of crop damage is crucial for understanding economic implications, devising effective agricultural strategies, and enhancing resilience amid mounting climate uncertainties. This study investigates the utility of Sentinel-1 Synthetic Aperture Radar (SAR) and Sentinel-2 MultiSpectral Instrument (MSI) data in tracking maize damage severity following typhoon events. By employing continuous field sampling techniques and conducting visual interpretation of high-resolution remote sensing imagery, sample sets representing a spectrum of maize damage severity were systematically established. The application of time series analysis on Sentinel data enables a comprehensive exploration of spectral and polarization responses, providing insights into the correlation with maize damage severity. Segmentation of the maize damage timeline into pre-disaster, disaster, and recovery periods, coupled with optimization of relevant feature parameters