The spatial sparsity and temporal discontinuity of station-based SAT data do not allow to fully understand Antarctic surface air temperature (SAT) variations over the last decades. Generating spatiotemporally continuous SAT fields using spatial interpolation represents an approach to address this problem. This study proposed a backpropagation artificial neural network (BPANN) optimized by a genetic algorithm (GA) to estimate the monthly SAT fields of the Antarctic continent for the period 1960–2019. Cross-validations demonstrate that the interpolation accuracy of GA-BPANN is higher than that of two benchmark methods, i.e., BPANN and multiple linear regression (MLR). The errors of the three interpolation methods feature month-dependent variations and tend to be lower (larger) in warm (cold) months. Moreover, the annual SAT had a significant cooling trend during 1960–1989 (trend = −0.07°C/year; ) and a significant warming trend during 1990–2019 (trend = 0.06°C/year; ). The monthly SAT did not show consistent cooling or warming trends in all months, e.g., SAT did not show a significant cooling trend in January and December during 1960–1989 and a significant warming trend in January, June, July, and December during 1990–2019. Furthermore, the Antarctic SAT decreases with latitude and the distance away from the coastline, but the eastern Antarctic is overall colder than the western Antarctic. Spatiotemporal inconsistencies on SAT trends are apparent over the Antarctic continent, e.g., most of the Antarctic continent showed a cooling trend during 1960–1989 (trend = −0.20∼0°C/year; ) with a peak over the central part of the eastern Antarctic continent, while the entire Antarctic continent showed a warming trend during 1990–2019 (trend = 0∼0.10°C/year; ) with a peak over the higher latitudes.

中文翻译：

---

基于 GA 的 BP 人工神经网络，用于估算 1960-2019 年南极月地表气温

基于站点的 SAT 数据的空间稀疏性和时间不连续性无法完全了解过去几十年南极表面气温 (SAT) 的变化。使用空间插值生成时空连续的 SAT 场代表了解决这个问题的一种方法。本研究提出了一种通过遗传算法 (GA) 优化的反向传播人工神经网络 (BPANN)，以估计 1960-2019 年期间南极大陆的每月 SAT 场。交叉验证表明 GA-BPANN 的插值精度高于两种基准方法，即 BPANN 和多元线性回归 (MLR)。三种插值方法的误差具有与月份相关的变化，并且在暖（冷）月中往往较低（较大）。而且，)和 1990-2019 年期间显着的变暖趋势（趋势 = 0.06°C/年；）。月度 SAT 并未在所有月份均呈现出一致的降温或升温趋势，例如 SAT 在 1960-1989 年的 1 月和 12 月未表现出明显的降温趋势，而在 1990 年期间的 1 月、6 月、7 月和 12 月则出现明显的升温趋势 - 2019。此外，南极 SAT 随纬度和距海岸线的距离而减小，但南极东部总体上比南极西部冷。南极大陆上SAT趋势的时空不一致很明显，例如，南极大陆大部分地区在1960-1989年期间呈现降温趋势（趋势=-0.20∼0°C/年；)在南极大陆东部中部出现高峰，而整个南极大陆在 1990-2019 年期间呈现变暖趋势（趋势 = 0∼0.10°C/年；)在高纬度地区出现峰值。