Airtime is crucial for high-rotation tricks in snowboard halfpipe performance, significantly impacting trick difficulty, the primary judging criterion. This study aims to enhance the detection of take-off and landing events using inertial measurement unit (IMU) data in conjunction with machine learning algorithms since manual video-based methods are too time-consuming. Eight elite German National Team snowboarders performed 626 halfpipe tricks, recorded by two IMUs at the lateral lower legs and a video camera. The IMU data, synchronized with video, were labeled manually and segmented for analysis. Utilizing a 1D U-Net convolutional neural network (CNN), we achieved superior performance in all of our experiments, establishing new benchmarks for this binary segmentation task. In our extensive experiments, we achieved an $80.34$% lower mean Hausdorff distance for unseen runs compared with the threshold approach when placed solely on the left lower leg. Using both left and right IMUs further improved performance ($83.37$% lower mean Hausdorff). For data from an algorithm-unknown athlete (Zero-Shot segmentation), the U-Net outperformed the threshold algorithm by $67.58$%, and fine-tuning on athlete-specific (Few-Shot segmentation) runs improved the lower mean Hausdorff to $78.68$%. The fine-tuned model detected takeoffs with median deviations of $0.008$ s (IQR $0.030$ s), landing deviations of $0.005$ s (IQR 0.020 s), and airtime deviations of $0.000$ s (IQR $0.027$ s). These advancements facilitate real-time feedback and detailed biomechanical analysis, enhancing performance and trick execution, particularly during critical events, such as take-off and landing, where precise time-domain localization is crucial for providing accurate feedback to coaches and athletes.

This study aimed (1) to assess the validity of a modified method (M_mod) based on heart rate (HR)—oxygen uptake (VO₂) regression functions to calculate total energy costs (W_total) and aerobic (W_aer) and anaerobic alactic energy contribution (W_pcr) and (2) to analyse the physiological and energetic demands of high-level pommel horse routines (PH routines). The M_mod was developed because VO₂ measurements are limited during high-level PH routines. Answering Part 1, nine male artistic gymnasts performed a PH routine where energy costs were calculated from VO₂ measurements and then compared with energy costs determined from the HR- VO₂ regressions of M_mod’s two additional tests. Using the concordance correlation coefficient (CCC) and Deming regression, W_aer (CCC = 0.955), W_pcr (CCC = 0.999), and W_total (CCC = 0.990) show substantial to almost perfect validity without constant or proportional bias. Data from eight further gymnasts performing a high-level PH routine and a graded exercise test (GXT), as well as four data sets from Part 1, were used to determine physiological and energetic demands using M_mod. VO₂ and HR during PH routines reached 86.1% and 90.4% of the maximal values during GXT. W_pcr was 47.0%, anaerobic lactic energy contribution (W_blc) was 29.7%, and W_aer was 23.3% of W_total required during PH routines. Summarising the energetic demands of high-level PH routines, they are mainly anaerobic, where W_pcr provides the largest energy share. W_aer provides a substantial part of W_total and should therefore also be specifically trained.

In snowboard freestyle disciplines, the amount of rotation is commonly determined as the sum of rotations around all board axes and is the most important indicator of the trick difficulty across all snowboard freestyle disciplines. Based on the type of rotation, tricks can be classified as flatspins, corks and flips. It is not yet known whether the type of rotation of a trick can influence the actual amount of rotation. Therefore, the aim of this study was to determine the amount of deviation, defined as difference between measured and assumed amount of rotation as a function of trick classification, using kinematic motion analysis. The amount of deviation was positive for flatspins (median: 21°; min: -4°; max: 49°) and negative for corks (median: -25°; min: -89°; max: 12°) and flips (median: -28°; min: -94°; max: 13°). Our results demonstrate that there are ways of execution where riders perform corks and flips with a shortcut and flatspins with a detour. This should be taken into account by judges, coaches and riders. Further research is needed to investigate how the shortcut can be influenced.

In the Olympic snowboard halfpipe discipline, rotation is the key indicator of trick difficulty encouraging riders to perform multiple tricks involving a high amount of rotation in their runs. Therefore, this study explored the predictive capacity of angular velocity and airtime on the amount of rotation using deterministic models based on the performance parameters of the Men's Final at the Beijing 2022 Olympic Winter Games. IMU data and video recordings were used to determine the biomechanical performance parameters of 122 tricks performed by 12 riders with random intercept models being employed to develop the aforementioned deterministic models. The ratio between angular velocity and airtime at frontside/switch frontside was greater than 4:1, and at backside/switch backside it was close to 5:1. The coefficient of determination overall indicated a high level of fit, providing significant standardised estimates for all performance parameters investigated. The results showed that, regardless of the direction of rotation, angular velocity was the key performance indicator for increasing the amount of rotation, while airtime showed a comparably small influence. These results are important for coaches and riders in teaching and learning new skills as they indicate to focus more on rotation initiation than increasing jump height.