Temporal patterns in the soundscape of the shallow waters of a Mediterranean marine protected area

Abstract

The study of marine soundscapes is an emerging field of research that contributes important information about biological compositions and environmental conditions. The seasonal and circadian soundscape trends of a marine protected area (MPA) in the Mediterranean Sea have been studied for one year using an autonomous acoustic recorder. Frequencies less than 1 kHz are dominated by noise generated by waves and are louder during the winter; conversely, higher frequencies (4-96 kHz) are dominated by snapping shrimp, which increase their acoustic activity at night during the summer. Fish choruses, below 2 kHz, characterize the soundscape at sunset during the summer. Because there are 13 vessel passages per hour on average, causing acoustic interference with fish choruses 46% of the time, this MPA cannot be considered to be protected from noise. On the basis of the high seasonal variability of the soundscape components, this study proposes a one-year acoustic monitoring protocol using the soundscape methodology approach and discusses the concept of MPA size.

Figure 1

Top: The study area (red arrow) at two scales: Topleft-Lampedusa Island in the Central Mediterranean Sea; Topright-Lampedusa Marine Protected Area (red arrow). Below: Capo Grecale MPA delimited by yellow buoys with the spacing shown. The recorder position (red point) was near the midpoint of the MPA. (Map source: Schlitzer, R., Ocean Data View, odv.awi.de, 2015).

Figure 2. Seasonal trends (one year of data from July 2013 until June 2014) in the rms octave band sound pressure levels (BPL) for different frequencies.

(a) Lower frequency BPL (from 62.5 to 1000 Hz). (b) Higher-frequency BPL from 2 kHz to 64 kHz. (Median; Whisker: 40^th–60^th).

Figure 3. Seasonal trends of rms BPLs for all data (one year), summer data (July, August and September) and winter data (December, January and February)(Median; Whisker: 45^th–55^th percentile).

The differences between the summer and winter for each BPL are significant (Mann-Whitney U test, p < 0.001).

Figure 4. BPLs for the daytime (10 am to 3 pm)and night-time (10 pm to 03 am; black line) for all four seasons (Median; Whisker: 40^th–60^th percentile).

Differences between daytime and night-time (black lines) are marked with *for p-level < 0.05), **for p-level < 0.01, ***for p-level < 0.0001 (Mann-Whitney U test). The light blue polygon in the Summer graph represents the acoustic niche of fish.

Figure 5. Circadian trends for each month in the BPLs (black line) and ACI (blue line) for three selected frequencies: 250, 1000 and 4000 Hz.

For 250 Hz and 1 kHz, the fish vocalization counts per minute were added to the secondary y-axis (grey area). For 4 kHz, the snap counts per minute from snapping shrimp (grey area) were added to the secondary y-axis. X-axis: hour of the day for each month.

Figure 6. BPLs from 62 to 2000 Hz calculated for 10-day subsamples between 7:30 pm and 11:30 pm for July and August (the period in which we recorded the maximum fish vocalization activity).

Median with 40% of the data (box) for fish choruses without vessel passage noise (green plot), with vessel passage noise (black plot) (46% of the recordings represented this condition), and for background noise (files with no fish chorus or vessel passage in the spectrogram) (median; Whisker: 30^th–70^th percentile).

Figure 7. Two-day continuous spectrogram (11 and 12 July 2014) showing the snapping shrimp sound (S), fish choruses (F) and anthropogenic noise caused by the passage of vessels (V).

The spectrogram was obtained using the XBAT software (Cornell University. USA). x-axis: time; y-axis: frequency 0–4 kHz; SPL intensity is shown in greyscale.