From 47275d485a98d90f4f8626471e72b989a8db7dbe Mon Sep 17 00:00:00 2001 From: Hillary Scannell Date: Fri, 27 Jul 2018 16:50:29 -0700 Subject: [PATCH] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index c4ae993..5134a76 100644 --- a/README.md +++ b/README.md @@ -27,7 +27,7 @@ This project involves tracking extreme and prolonged warming events in sea surfa | SARIMAX | Seasonal AutoRegressive Integrated Moving Average with eXogenous regressors, order(6,2,1)(6,2,1,4) | MSE = 0.13 | | Persistence | "walk-forward" validation | MSE = 0.28 (1-day), 0.29 (3-day), 0.65 (9-day) | |LSTM_1var | 5 neuron LSTM, 1 neuron Dense output layer, tanh activation, SGD optimizer, fit with 20 epochs, 520 batch size, forecasting 5-day sequence based on the previous 20 days, features are only SST | | -| LSTM_adjacent | LSTM trained on the SST from a neighboring grid cells | *in prog.*| +| LSTM_adjacent | LSTM trained on the SST from a neighboring grid cells | | | LSTM_5var | 30 neuron LSTM, 1 neurton Dense output, tanh activation, SGD optimizer, 20 epochs, 800 batch_size, forecasting 21-day sequences based on the previous 100 days, features include SST, AirT, RH, WS, and SLP | | | LSTM_2var_PCA | features include SST and the first 2 PCs of SST, AirT, RH, WS and SLP | | | XGB_1var_binary | Gradient Boosted Machines for event classification using SST alone to predict marine heatwave class, labels are binary (0=no event, 1=MHW), forecasts 30 days using the past 40, weights are given to circumvent class imbalance |