اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدFeature Importance in a Deep Learning Climate Emulator
308
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
We present a study using a class of post-hoc local explanation methods i.e., feature importance methods for understanding a deep learning (DL) emulator of climate. Specifically, we consider a multiple-input-single-output emulator that uses a DenseNet encoder-decoder architecture and is trained to predict interannual variations of sea surface temperature (SST) at 1, 6, and 9 month lead times using the preceding 36 months of (appropriately filtered) SST data. First, feature importance methods are employed for individual predictions to spatio-temporally identify input features that are important for model prediction at chosen geographical regions and chosen prediction lead times. In a second step, we also examine the behavior of feature importance in a generalized sense by considering an aggregation of the importance heatmaps over training samples. We find that: 1) the climate emulators prediction at any geographical location depends dominantly on a small neighborhood around it; 2) the longer the prediction lead time, the further back the importance extends; and 3) to leading order, the temporal decay of importance is independent of geographical location. An ablation experiment is adopted to verify the findings. From the perspective of climate dynamics, these findings suggest a dominant role for local processes and a negligible role for remote teleconnections at the spatial and temporal scales we consider. From the perspective of network architecture, the spatio-temporal relations between the inputs and outputs we find suggest potential model refinements. We discuss further extensions of our methods, some of which we are considering in ongoing work.
قيم البحث
اقرأ أيضاً
The problem of explaining deep learning models, and model predictions generally, has attracted intensive interest recently. Many successful approaches forgo global approximations in order to provide more faithful local interpretations of the models b
ehavior. LIME develops multiple interpretable models, each approximating a large neural network on a small region of the data manifold and SP-LIME aggregates the local models to form a global interpretation. Extending this line of research, we propose a simple yet effective method, NormLIME for aggregating local models into global and class-specific interpretations. A human user study strongly favored class-specific interpretations created by NormLIME to other feature importance metrics. Numerical experiments confirm that NormLIME is effective at recognizing important features.
Supernova spectral time series contain a wealth of information about the progenitor and explosion process of these energetic events. The modeling of these data requires the exploration of very high dimensional posterior probabilities with expensive r
adiative transfer codes. Even modest parametrizations of supernovae contain more than ten parameters and a detailed exploration demands at least several million function evaluations. Physically realistic models require at least tens of CPU minutes per evaluation putting a detailed reconstruction of the explosion out of reach of traditional methodology. The advent of widely available libraries for the training of neural networks combined with their ability to approximate almost arbitrary functions with high precision allows for a new approach to this problem. Instead of evaluating the radiative transfer model itself, one can build a neural network proxy trained on the simulations but evaluating orders of magnitude faster. Such a framework is called an emulator or surrogate model. In this work, we present an emulator for the TARDIS supernova radiative transfer code applied to Type Ia supernova spectra. We show that we can train an emulator for this problem given a modest training set of a hundred thousand spectra (easily calculable on modern supercomputers). The results show an accuracy on the percent level (that are dominated by the Monte Carlo nature of TARDIS and not the emulator) with a speedup of several orders of magnitude. This method has a much broader set of applications and is not limited to the presented problem.
Given the importance of public support for policy change and implementation, public policymakers and researchers have attempted to understand the factors associated with this support for climate change mitigation policy. In this article, we compare t
he feasibility of using different supervised learning methods for regression using a novel socio-economic data set which measures public support for potential climate change mitigation policies. Following this model selection, we utilize gradient boosting regression, a well-known technique in the machine learning community, but relatively uncommon in public policy and public opinion research, and seek to understand what factors among the several examined in previous studies are most central to shaping public support for mitigation policies in climate change studies. The use of this method provides novel insights into the most important factors for public support for climate change mitigation policies. Using national survey data, we find that the perceived risks associated with climate change are more decisive for shaping public support for policy options promoting renewable energy and regulating pollutants. However, we observe a very different behavior related to public support for increasing the use of nuclear energy where climate change risk perception is no longer the sole decisive feature. Our findings indicate that public support for renewable energy is inherently different from that for nuclear energy reliance with the risk perception of climate change, dominant for the former, playing a subdued role for the latter.
Gradient-based attribution methods can aid in the understanding of convolutional neural networks (CNNs). However, the redundancy of attribution features and the gradient saturation problem, which weaken the ability to identify significant features an
d cause an explanation focus shift, are challenges that attribution methods still face. In this work, we propose: 1) an essential characteristic, Strong Relevance, when selecting attribution features; 2) a new concept, feature map importance (FMI), to refine the contribution of each feature map, which is faithful to the CNN model; and 3) a novel attribution method via FMI, termed A-FMI, to address the gradient saturation problem, which couples the target image with a reference image, and assigns the FMI to the difference-from-reference at the granularity of feature map. Through visual inspections and qualitative evaluations on the ImageNet dataset, we show the compelling advantages of A-FMI on its faithfulness, insensitivity to the choice of reference, class discriminability, and superior explanation performance compared with popular attribution methods across varying CNN architectures.
Class Activation Mapping (CAM) is a powerful technique used to understand the decision making of Convolutional Neural Network (CNN) in computer vision. Recently, there have been attempts not only to generate better visual explanations, but also to im
prove classification performance using visual explanations. However, the previous works still have their own drawbacks. In this paper, we propose a novel architecture, LFI-CAM, which is trainable for image classification and visual explanation in an end-to-end manner. LFI-CAM generates an attention map for visual explanation during forward propagation, at the same time, leverages the attention map to improve the classification performance through the attention mechanism. Our Feature Importance Network (FIN) focuses on learning the feature importance instead of directly learning the attention map to obtain a more reliable and consistent attention map. We confirmed that LFI-CAM model is optimized not only by learning the feature importance but also by enhancing the backbone feature representation to focus more on important features of the input image. Experimental results show that LFI-CAM outperforms the baseline modelss accuracy on the classification tasks as well as significantly improves on the previous works in terms of attention map quality and stability over different hyper-parameters.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
