Deep neural networks (DNNs) have driven the recent advances in fire detection. However, existing methods require large-scale labeled samples to train data-hungry networks, which are difficult to collect and even more laborious to label. This paper applies unsupervised domain adaptation (UDA) to transfer knowledge from a labeled public fire dataset to another unlabeled one in practical application scenarios for the first time. Then, a transfer learning benchmark dataset called Fire-DA is built from public datasets for fire recognition. Next, the Deep Subdomain Adaptation Network (DSAN) and the Dynamic Adversarial Adaptation Network (DAAN) are experimented on Fire-DA to provide a benchmark result for future transfer learning research in fire recognition. Finally, two transfer tasks are built from Fire-DA to two public forest fire datasets, the aerial forest fire dataset FLAME and the large-scale fire dataset FD-dataset containing forest fire scenarios. Compared with traditional handcrafted feature-based methods and supervised CNNs, DSAN reaches 82.5% performance of the optimal supervised CNN on the testing set of FLAME. In addition, DSAN achieves 95.8% and 83.5% recognition accuracy on the testing set and challenging testing set of FD-dataset, which outperform the optimal supervised CNN by 0.5% and 2.6%, respectively. The experimental results demonstrate that DSAN achieves an impressive performance on FLAME and a new state of the art on FD-dataset without accessing their labels during training, a fundamental step toward unsupervised forest fire recognition for industrial applications.
Global geomagnetic field models typically have low spatial resolution, whereas regional models are constrained by boundary effects and limited truncation levels. To address these limitations, this study introduces a novel regional geomagnetic anomaly field model called the regional associated Legendre polynomials magnetic model (R−ALPOLM). This model employs the associated Legendre polynomials method, which combines the QR decomposition approach and a comprehensive evaluation index formula to enhance the computational efficiency of parameter estimation. In addition, it allows for scientific and intuitive determination of the optimal truncation level of the model. The overall prediction accuracy of the model is significantly enhanced by identifying and re-predicting outliers using the exponential moving average approach. The results indicate that the degree 83 R−ALPOLM achieves a root mean square error (RMSE) of 3.21 nT. Compared to traditional models, the proposed model exhibits lower error rates, highlighting its superior efficiency and predictive accuracy. This underscores the potential value of the proposed model in both scientific research and practical applications.