Mamba has recently emerged as a promising alternative to Transformers, offering near-linear complexity in processing sequential data. However, while channels in time series (TS) data have no specific order in general, recent studies have adopted Mamba to capture channel dependencies (CD) in TS, introducing a sequential order bias. To address this issue, we propose SOR-Mamba, a TS forecasting method that 1) incorporates a regularization strategy to minimize the discrepancy between two embedding vectors generated from data with reversed channel orders, thereby enhancing robustness to channel order, and 2) eliminates the 1D-convolution originally designed to capture local information in sequential data. Furthermore, we introduce channel correlation modeling (CCM), a pretraining task aimed at preserving correlations between channels from the data space to the latent space in order to enhance the ability to capture CD. Extensive experiments demonstrate the efficacy of the proposed method across standard and transfer learning scenarios. Time series (TS) forecasting is prevalent in various fields, including weather (Angryk et al., 2020), traffic (Cirstea et al., 2022), and energy (Dudek et al., 2021). While Transformers (Vaswani et al., 2017) have been widely employed for this task due to their ability to capture long-term dependencies in sequences (Wen et al., 2022), their quadratic computational complexity causes substantial computational overhead, limiting their practicality in real-world applications.

In the hope of making drone deliveries even more accurate, Project Wing has started making deliveries directly to people's houses in southeastern Australia. The firm announced that it will deliver food from Mexican food chain, Guzman y Gomez, and medicines from Chemist Warehouse pharmacies to customers in rural areas on the border of the Australian Capital Territory and New South Wales. Project Wing, which is run by Google parent Alphabet, hopes the trials will help to fine-tune how its drones move goods from where they're located to where they're needed. In the hope of making drone deliveries even more accurate, Alphabet's Project Wing has started making deliveries directly to people's houses in southeastern Australia Project Wing's aircraft has a wingspan of approximately 1.5m (4.9ft) and have four electrically-driven propellers. The total weight, including the package to be delivered, is approximately 10kg (22lb). The aircraft itself accounts for the bulk of that at 8.5kg (18.7lb).