Compounding Approaches for Wind Prediction From Underwater Noise by Supervised Learning

Trucco, A.; Barla, Annalisa; Bozzano, Roberto; Fava, Emanuele; Pensieri, Sara; Verri, Alessandro; Solarna, David

doi:10.1109/joe.2022.3162689

Cited by 3 publications

(19 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, Taylor et al [15] proposed random forest (RF) and CatBoost to predict wind and rainfall from hourly averaged noise spectra. RF [16], [17] was also used in [18] for rainfall detection from hourly averaged noise spectra, as well as in [19] for wind prediction. In the latter case, the averaging of predictions obtained from instantaneous noise spectra (i.e., prediction compounding) was adopted because it provided better performance than the traditional averaging of spectra (i.e., spectral compounding) before the prediction.…”

Section: Introductionmentioning

confidence: 99%

“…The acoustic data are synchronized with measurements of wind speed and rainfall intensity taken at the same location, using a sonic anemometer and a rain gauge mounted 10 m above sea level. This data set has already been used to predict hourly averages of wind speed and rainfall intensity [11], [15], [18], [19] by applying both empirical equations and ML techniques, in both cases without considering temporal memory. The best results for wind prediction are those reported in [19] where the RF regression [16], [17] and the average of consecutive predictions (namely, six predictions at 10-min intervals were averaged to yield the hourly average) were adopted.…”

Section: Introductionmentioning

confidence: 99%

“…This data set has already been used to predict hourly averages of wind speed and rainfall intensity [11], [15], [18], [19] by applying both empirical equations and ML techniques, in both cases without considering temporal memory. The best results for wind prediction are those reported in [19] where the RF regression [16], [17] and the average of consecutive predictions (namely, six predictions at 10-min intervals were averaged to yield the hourly average) were adopted. For rainfall prediction, the best results in [15] were obtained with an RF regressor fed by the hourly averaged spectra, using only a fraction of the mentioned data set.…”

Section: Introductionmentioning

confidence: 99%

“…For rainfall prediction, the best results in [15] were obtained with an RF regressor fed by the hourly averaged spectra, using only a fraction of the mentioned data set. Both in [15] and [19], as well as in all other papers using underwater noise, only noise samples collected during the interval in which the wind or rainfall is predicted are exploited. In contrast, the LSTM network [37], [38] is used in this work to model the temporal correlation of the two meteorological phenomena under consideration and exploit antecedent noise samples for their prediction.…”

Section: Introductionmentioning

confidence: 99%

“…K−1 subsets are used for the model training and the remaining one to test it; this is repeated until each subset has been used to test the model [17]). For comparison, the same testing approach is applied to an RF regressor, which is considered by the literature to be one of the best options [15], [19] when temporal memory is not considered. With both LSTM and RF, six consecutive predictions are averaged [19] to compute the hourly average of wind speed and rainfall intensity.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Introducing Temporal Correlation in Rainfall and Wind Prediction From Underwater Noise

Trucco

Barla

Bozzano

et al. 2023

IEEE J. Oceanic Eng.

View full text Add to dashboard Cite

While in the past the prediction of wind and rainfall from underwater noise was performed using empirical equations fed with very few spectral bins and fitted to the data, it has recently been shown that regression performed using supervised machine learning techniques can benefit from the simultaneous use of all spectral bins, at the cost of increased complexity. However, both empirical equations and machine learning regressors perform the prediction using only the acoustic information collected at the time when one wants to know the wind speed or the rainfall intensity. At most, averages are made between spectra measured at subsequent times (spectral compounding) or between predictions obtained at subsequent times (prediction compounding). In this article, it is proposed to exploit the temporal correlation inherent in the phenomena being predicted, as has already been done in methods that forecast wind and rainfall from their values (and sometimes those of other meteorological quantities) in the recent past. A special architecture of recurrent neural networks, the long shortterm memory, is used along with a data set composed of about 16 months of underwater noise measurements (acquired every 10 min, simultaneously with wind and rain measurements above the sea surface) to demonstrate that the introduction of temporal correlation brings significant advantages, improving the accuracy and reducing the problems met in the widely adopted memoryless prediction performed by random forest regression. Working with samples acquired at 10-min intervals, the best performance is obtained by including three noise spectra for wind prediction and six spectra for rainfall prediction.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Introducing Temporal Correlation in Rainfall and Wind Prediction From Underwater Noise

Trucco

Barla

Bozzano

et al. 2023

IEEE J. Oceanic Eng.

View full text Add to dashboard Cite

show abstract

Oil Spill Timely Backtracking Oriented by Wind Field Correction With Self-Attention Temporal Convolutional Networks

Li,

Lyu,

Ren

2024

IEEE J. Oceanic Eng.

View full text Add to dashboard Cite

Listening for rain: Principal component analysis and linear discriminant analysis for broadband acoustic rainfall detection

Mallary,

Berg,

Buck

et al. 2023

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

Rain falling on the ocean creates acoustic signals. Ma and Nystuen [(2005). J. Atmos. Oceanic Technol. 22, 1225–1248] described an algorithm that compares three narrowband “discriminant” frequencies to detect rain. In 2022, Trucco, Bozzano, Fava, Pensieri, Verri, and Barla [(2022). IEEE J. Oceanic Eng. 47(1), 213–225] investigated rain detection algorithms that use broadband spectral data averaged over 1 h. This paper implements a rainfall detector that uses broadband acoustic data at 3-min time resolution. Principal Component Analysis (PCA) reduces the dimensionality of the broadband data. Rainfall is then detected via a Linear Discriminant Analysis (LDA) on the data's principal component projections. This PCA/LDA algorithm was trained and tested on 5 months of data recorded by hydrophones in a shallow noisy cove, where it was not feasible to average spectral data over 1 h. The PCA/LDA algorithm successfully detected 78 ± 5% of all rain events over 1 mm/h, and 73 ± 5% of all rain events over 0.1 mm/h, for a false alarm rate of ≈ 1% in both cases. By contrast, the Ma and Nystuen algorithm detected 32 ± 5% of the rain events over 1.0 mm/h when run on the same data, for a comparable false alarm rate.

show abstract

Compounding Approaches for Wind Prediction From Underwater Noise by Supervised Learning

Cited by 3 publications

References 0 publications

Introducing Temporal Correlation in Rainfall and Wind Prediction From Underwater Noise

Introducing Temporal Correlation in Rainfall and Wind Prediction From Underwater Noise

Oil Spill Timely Backtracking Oriented by Wind Field Correction With Self-Attention Temporal Convolutional Networks

Listening for rain: Principal component analysis and linear discriminant analysis for broadband acoustic rainfall detection

Contact Info

Product

Resources

About