Switching-aware spectrum selection requires balancing interference avoidance against retuning costs. This paper evaluates a hybrid neural–polynomial deep Q-network (HNP-DQN) in an eight-channel, measurement-driven 5 GHz testbed with exogenous sweeping and random interference. The architecture combines learned latent features with an element-wise second-order expansion, layer normalization (LayerNorm), and a dueling Double Deep Q-Network (DDQN) backbone. Files are separated before window construction, and the evaluation includes a pre-inspected pilot and two outcome-uninspected distance and power transfers. The comparison includes strong deterministic rules and a capacity-matched multilayer perceptron (MLP) trained with the same DDQN procedure. All methods are evaluated on common trajectories with paired inference across 10 independently trained seeds and Holm correction. Under deterministic sweeping, the schedule-aware rule was given the declared initial phase and one-channel-per-step direction and used an internal step counter to track the deterministic progression. These schedule variables and the corresponding step index are absent from HNP-DQN’s 48-dimensional observation. The rule matched the trajectory-wise dynamic-programming upper bound and outperformed HNP-DQN in all three settings (differences calculated as HNP-DQN minus the rule: $-1.91$, $-3.51$, and $-1.97$; all adjusted $p=0.023$). This information-asymmetric operational comparison shows the advantage attainable when the declared sweep specification and its progression are directly exploited; however, it does not provide a matched-information architectural ranking. By contrast, under random jamming, all comparisons between HNP-DQN and the threshold rule were inconclusive after correction, as were all six capacity-matched comparisons between HNP-DQN and the MLP. Of the 24 exploratory ablation comparisons, one favored the $\gamma =0$ variant in the random pilot, whereas the other 23 were inconclusive. Accordingly, this paper provides an information-aware, approximately parameter-matched reference for evaluating when explicit knowledge, observation-based control, or additional learning complexity is justified within the declared measurement-replay scope.

Accurate Short-term forecasting of gusts at 10 m above ground level is challenging because gridded meteorological variables exhibit persistence, nonstationarity, and abrupt transitions. This study proposes a Temporal Adaptive Difference Polynomial Network (TADPN) using 8760 hourly records from a representative Nanjing grid point in 2025. Surface and pressure-level predictors are temporally aligned ECMWF IFS HRES 9 km fields retrieved through the default Best Match option of the Open-Meteo Historical Weather API, with a 12 h input window. TADPN uses the current gust as a persistence anchor and decomposes the forecast increment into a basic-trend component and a difference polynomial perturbation component. The basic branch uses all 60 variables, whereas the perturbation branch constructs current states, first- and second-order differences, signed-square terms, and within-variable interactions from 18 wind-related variables, with variable- and term-level soft gates. Strictly chronological three-fold rolling validation yields mean MAE, RMSE, and $R^2$ values of 0.4197 m s⁻¹, 0.6079 m s⁻¹, and 0.9373. TADPN reduces MAE by 11.88–29.88% relative to nine baselines. Ablation and significance analyses support the perturbation branch and difference-based features, demonstrating a lightweight and interpretable framework for hourly single-grid gust forecasting.

Snow plays a significant role in the global energy balance, climate change, hydrological cycles, and other areas. However, traditional surface observation methods are limited in capturing the spatiotemporal dynamics of snow. This paper systematically reviews Machine Learning algorithms applicable to snow cover recognition. It highlights traditional Machine Learning methods such as Support Vector Machines and Random Forests, as well as more semantically oriented Deep Learning methods, including CNNs, attention mechanisms, and Transformers. These methods have shown robust performance in the domain of snow identification. Lastly, the paper discusses the strengths and weaknesses of different approaches and suggests directions for future research. Through this paper, readers will gain a comprehensive understanding of Machine Learning-based snow recognition algorithms and how these algorithms can be leveraged better.