Fish Production Data Research Articles

Comparing ARIMA, Neural Network and Hybrid Models for Forecasting Fish Production in Bangladesh

Time series forecasting is a commonly applied method for scientific predictions. There are several econometric methods for forecasting time series observations and predicting the systematic pattern of underlying data. ARIMA model is most renowned in this aspect for its linearity. Nowadays a machine learning model namely artificial neural network (ANN) is gaining popularity for its nonlinear characteristics. Inconsistent conclusions may frequently be drawn when evaluating whether ARIMA models or neural networks are better at forecasting future events. For this reason, a hybrid methodology has been established in this study to get advantage from both linear and nonlinear modeling. The annual dataset of fish production in Bangladesh from 1990 to 2020 has been evaluated in this case. Formulating three measurement errors, RMSE, MAE and MAPE it has been demonstrated that the hybrid approach has high level of forecasting accuracy than the other two models in forecasting fish production data. Dhaka Univ. J. Sci. 72(1): 71-76, 2024 (January)

Estimation of The Potential of Large Pelagic Fish Fisheries Using Satellite Data in The Banda and Arafura Seas

The Banda and Arafura Sea possesses significant potential for the fisheries and fishing industry in the country. The large pelagic fish production data studied were derived from satellite imagery data in the Banda and Arafura Seas (2002-2022). The data of chlorophyll-a content, sea surface temperature and Photosynthetically Available Radiation (PAR) derived from AQUA MODIS satellite images were used to estimate the value of primary productivity with the Vertically Generalised Production Model (VGPM). The results showed that the biomass of large pelagic fish fluctuated seasonally, with the Banda Sea and Arafura Sea having high average fish biomass values in the eastern season. With the highest fish biomass peak in August and the lowest in December. The high value of fish biomass in the Banda Sea and Arafura Sea is caused by upwelling events where sea surface temperatures are low but chlorophyll is high. in the Arafura Sea the value of fish biomass is higher than the Banda Sea, this is due to the large amount of nutrient input from large rivers in the area.

Does fish production influence the GDP and food security in Gulf Cooperation Council countries? Evidence from the dynamic panel data analysis

The significance of fish production in human life has been proven in terms of food security as well as in increasing fishery income and economic growth. This study investigates the model of the long-run connection between marine fish production, economic growth, and food security. The study applies an annual panel data set comprising six Gulf Cooperation Council countries, covering the sample period 2000–2019. We have selected marine fish production as most of the fish production in the Gulf region is originated from marine sources with broad geographic distribution and better accessibility of marine fish production data. Testing the recently developed panel unit root tests, cointegration test, and the heterogeneous dynamic panel data named as a mean group, pooled mean group, and dynamic fixed effect estimation techniques on cross-country panel data, the result confirms the theoretical hypothesis of a positive relationship between fish export and GDP and fish import and food security. The Hausman tests suggest that the pooled mean group results are the appropriate ones. Further studies need to re-investigate the potential of fish production in explaining the economic growth and food security to meet the fast-growing population in Gulf Cooperation Council countries.

PEMODELAN SPASIAL PRODUKSI IKAN PADA INDUSTRI BUDIDAYA PERIKANAN DI KOTA CILEGON

The aquaculture industry in Cilegon City is fairly substantial. In the year 2020, 230.09 tons of farmed fish were produced. In Cilegon City, fish production statistics is often used for each sub-district. So far, no research has been undertaken to examine the dependency of fish output from one district to the next. Spatial modeling is used to examine the spatial correlation of fish production data in each sub-district, making it easier to characterize observations in a sub-district and their relationships with other sub-districts. A semivariogram model was fitted using the fish production data, and it was discovered that fish production in the city of Cilegon followed the cubic model with model parameters C = 2.9891 and range a = 5.28. Furthermore, using this spatial model, assessment of fish production in a location, in this example Cilegon City, can be carried out in further research in an effort to see food security.

Forecasting of Indonesian Annual Protein Demand for Nile Tilapia (Oreochromis niloticus) Using Exponential Smoothing

The need for protein or the amount of protein needed by the fish sector in Indonesia has never been recorded and known. Although the demand for protein in aquatic feeds is very high, data related to protein requirements for fish feed in Indonesia need to be known for determining the urgency of providing protein substitutes in feed. So, it is necessary to predict feed and protein demand based on a series of fish production data. This study predicted the protein demand for Nile tilapia (Oreochromis niloticus). Three exponential smoothing approaches, namely, single, double, and triple exponential smoothing, were applied to obtain the best model for production estimation. The protein demand was analyzed based on feed conversion ratio and standard protein content in the Nile feed by knowing the production. Production decreased dramatically in 2020. The best approach for predicting is triple exponential smoothing, which predicted a gradual increase of Nile production in 2021. The protein demand for the next five years (2025) is about 345,331.50 to 690,663.00 tons in the scenario of FCR 1.2 and 2.0. It is the first report on predicting protein demand for the production of Nile tilapia. Thus, the government needs to prepare the fulfillment of protein needs for the tilapia fish.

An adaptive method for fish growth prediction with empirical knowledge extraction

Fish growth prediction provides important information for optimising production in aquaculture. Fish usually exhibit different growth characteristics due to the variations in the environment, the equipment used in different fish workshops and inconsistent application by operators of empirical rules varying from one pond to another. To address this challenge, the aim of this study is to develop an adaptive fish growth prediction method in response to feeding decision. Firstly, the practical operational experience in historical feeding decisions for different fish weights is extracted to establish the feeding decision model. Then, a fish weight prediction model is established by regression analysis methods based on historical fish production data analysis. The feeding decision model is integrated as the input information of the fish weight prediction model to obtain fish weight prediction. Furthermore, an adaptive fish growth prediction strategy is proposed by continuously updating model parameters using new measurements to adapt to specific characteristics. The proposed adaptive fish growth prediction method with empirical knowledge extraction is evaluated by the collected production data of spotted knifejaw ( Oplegnathus punctatus ). The results show that established models can achieve a good balance between goodness-of-fit and model complexity, and the adaptive prediction method can adapt to specific fish pond's characteristics and provide a more effective way to increase fish weight prediction accuracy. The proposed method provides an important contribution to achieving adaptive fish growth prediction in a real time from the view of aquaculture practice for spotted knifejaw. • The feeding decision model is established by empirical knowledge extraction. • The fish weight prediction is obtained by regression analysis method. • The adaptive updating strategy is proposed to adapt to specific characteristics. • The production data of spotted knifejaw is used to model and verify method.

Comparison of Exponential Smoothing Methods for Forecasting Marine Fish Production in Pekalongan Waters, Central Java

Pekalongan waters, a part of the Java Sea, has potency to develop marine fisheries sector to increase regional income and community livelihoods. The fluctuation of marine fish production every year requires serious attention in planning and policy strategies for the utilization of the fishery resources. Time series fish production data can be used to predict fish production in the following years through the forecasting process. The data used in this study is fish production data from Pekalongan Fishing Port, Central Java, from January 2011 to December 2020. The method used is data exponential smoothing by comparing three exponential smoothing methods consisting of single/simple exponential smoothing, double exponential smoothing and Holt-Winters’ exponential smoothing. The criterion that used to measure the forecasting performance is the mean absolute percentage error (MAPE) value. The smaller MAPE value shows the better the forecasting result. The smallest MAPE value is obtained by finding the optimal smoothing constant value which is usually calculated using the trial and error method. However, in this study, the constant value was calculated using the add-in solver approach in Microsoft Excel. The forecasting results obtained show that forecasting using the Holt Winter Exponential Smoothing method is reasonable with a MAPE value of 37.878.

ECOLOGY AND FISHERY STATUS OF UKAI RESERVOIR, GUJARAT

The study dealt with the ecology and fish diversity of Ukai reservoir, Gujarat, which was undertaken during July 2014 to August 2015. During the study 50 fish species belonging to 9 orders, 17 families and 38 genera were recorded. The order Cypriniformes was dominant with 22 species followed by Siluriformes with 12 species. The most abundant species in the reservoir were Catla catla, Labeo rohita, Cirrhinus mrigala, Labeo calbasu, Wallago attu, Sperata aor, Systomus sarana, Clupisoma garua, Macrobrachium rosenbergii and Ompok bimaculatus. A total 34 lakh fingerlings of Indian major carps namely catla, rohu and mrigal were stocked in the reservoir during 2013-14, which reflects in the production trend. Fish production data (2014-15) of the reservoir showed that carps contributed 50.68% of the total production followed by catfishes 10.04%, murrels 3.0%, eels 2.86 and others 33.43% with productivity of the reservoir at 279 kg ha -1. Species like Tenualosa ilisha, Tor tor, S. seenghala, S. aor, Labeo fimbriatus and W. attu gradually decreased over the years after impoundment. The study indicated that Ukai reservoir is rich in fish diversity Regular stocking, fishing ban during breeding season, etc. would sustain the fish diversity of the reservoir. Key words: Ecology, fish diversity, Ukai reservoir, management measures, Gujarat

Developing an Ensembled Machine Learning Prediction Model for Marine Fish and Aquaculture Production

The fishing industry is identified as a strategic sector to raise domestic protein production and supply in Malaysia. Global changes in climatic variables have impacted and continue to impact marine fish and aquaculture production, where machine learning (ML) methods are yet to be extensively used to study aquatic systems in Malaysia. ML-based algorithms could be paired with feature importance, i.e., (features that have the most predictive power) to achieve better prediction accuracy and can provide new insights on fish production. This research aims to develop an ML-based prediction of marine fish and aquaculture production. Based on the feature importance scores, we select the group of climatic variables for three different ML models: linear, gradient boosting, and random forest regression. The past 20 years (2000–2019) of climatic variables and fish production data were used to train and test the ML models. Finally, an ensemble approach named voting regression combines those three ML models. Performance matrices are generated and the results showed that the ensembled ML model obtains R2 values of 0.75, 0.81, and 0.55 for marine water, freshwater, and brackish water, respectively, which outperforms the single ML model in predicting all three types of fish production (in tons) in Malaysia.

VARIABILITY OF SEA SURFACE TEMPERATURE AT FISHERIES MANAGEMENT AREA 715 IN INDONESIA AND ITS RELATION TO THE MONSOON, ENSO AND FISHERY PRODUCTION

Sea surface temperature (SST) is one of the important oceanographic and climatemparameters. Its variability and anomaliesmoften influence the environment and organisms, both in the oceansand on land. This study aims to identifythe variability of SST and help the fisheries community to understand how climate phenomena such as ENSOand monsoonal phases (represented by wind speed) are related to SST and fishery production in Fisheries Management Area (FMA)715.SST was measured at Parimo, which represents conditionsinthe western partof the areainside Tomini Bay,and at Bitung, which represents SST in the open ocean,with a more exposuredgeographical position. SST wasderived from MODIS satellite imagery, downloaded from the ocean color database (https://oceancolor.gsfc.nasa.gov/) with a4 km spatial resolution, from January 2009 to December 2018. Wind speed data, historical El Niño or La Niña events,and fish production data were also used in the study. Pearson’s correlation (Walpole, 1993) was used to test the relationship between SST variability or anomaly and ENSO and monsoons. The results show that the SST characteristics and variability of the Parimo and Bitung watersare very different, although they bothliein the same FMA 715. SST in Parimo waters is warmer,but with lower variability than in Bitung waters. SST in Parimo has a lowcorrelation with ENSO (r=0.06, n=66), low correlation with wind speed (r=-0.29, n=120),with also a lowcorrelation between SST anomaly and ENSO (r=0.05, n=66). SST in Bitung has a higher, but inverse, correlation with ENSO (r=-0.53, n=66), highcorrelation with wind speed (r=-0.60, n=119), with also a high correlation between SST anomaly and ENSO (r=-0.74, n=66). Unlike in other parts of Indonesia, fishery production in Parimo,or the western part inside Tomini Bay,is not affected by ENSO events

Small-Scale Fisheries Production And Rural Livelihoods: A Case Of Lake Mutirikwi (Lake Kyle), Zimbabwe

This study was conducted on Lake Mutirikwi, Zimbabwe, to determine the annual fish production and the role of small-scale fisheries in rural livelihoods. Fish production data (catch and effort) were obtained from fishers’ records. Information on fishers’ demographics and livelihoods was obtained through a questionnaire survey. A total of 30 fishers were interviewed.

SISTEM BASIS DATA PRODUKSI IKAN BERBASIS SITUS WEB (WEBSITE) DI KABUPATEN SUKABUMI – JAWA BARAT

Faktor pendorong terciptanya sistem basis data produksi ikan adalah lahirnya kebijakan yang diterbitkan Pemerintah, yaitu UU No. 45 tahun 2009 tentang Perikanan pasal 46 ayat 1 dan 2. Permasalahan yang ada di Dinas Kelautan dan Perikanan Kabupaten Sukabumi adalah tidak adanya sistem basis data produksi ikan berbasis situs web (website) yang mencakup Pangkalan Pendaratan Ikan (PPI). Tujuan dari penelitian ini adalah menyusun sistem basis data produksi ikan berbasis situs web (website) di pelabuhan perikanan kelas D (PPI). Metode yang digunakan dalam penelitian ini adalah metode pembuatan prototipe (prototyping). Keunggulan dari sistem basis data produksi ikan berbasis situs web (website) adalah kemampuan mengintegrasikan perhitungan dari produksi ikan per bulan, sehingga tidak perlu melakukan perhitungan atau memasukan (input) data produksi ikan per tahun. Berdasarkan hasil penelitian, sistem basis data produksi ikan berbasis situs web (website) mencakup empat Pangkalan Pendaratan Ikan (PPI) di Teluk Palabuhanratu, diantaranya PPI Cisolok, PPI Ciwaru, PPI Ujung Genteng, dan PPI Mina Jaya. Investor, nelayan, pengolah ikan, peneliti, dan masyarakat dapat mengakses data dan informasi produksi ikan di situs web (website) melalui menu produksi ikan per bulan, menu produksi ikan per tahun, menu produksi ikan selama beberapa tahun.

Profile of Salted Fish Processing in Pengolahan Hasil Perikanan (PHPT) Muara Angke

The quality of salted fish depends on the quality of raw material as well as the processing methods. The aim of this work was to study the processing profile of the salted fish in PHPT Muara Angke. Data was collected from the annual salted fish production data in Muara Angke from January 2017 to July 2018, as well as from observation and interview with 25 salted fish producers using snowball sampling method. The results showed that the processed fish species were very diverse and the processing was carried out using traditional methods. Frozen fish were used more frequently than the fresh one. The ground water and crystal salt were used in the processing.Pickling was widely used for salting method rather than dry salting or wet salting. Drying of the fish was carried out traditionally under the sun. However, bleaching agent was still used by some producers. In conclusion, the processing of salted fish in PHPT Muara Angke has not appliedsanitized and hygiene production processes.

Trends in marine fish production in Tamil Nadu using regression and autoregressive integrated moving average (ARIMA) model

Tamil Nadu is situated in the south eastern coast of the Indian peninsula with a coastal line of 1076 km (13% of the country’s coast line), 0.19 million sq.km of EEZ (9.4 % of total national EEZ) and a continental shelf of about 41,412 sq. km. This is one of the country’s leading state in marine fish production and ranks third in marine fish production. In Tamil Nadu, Ramanathapuram district is a leading maritime district followed by Nagapattinam and Thoothukudi. The objective of this study was to investigate the trends in marine fish production in Tamil Nadu. Yearly fish production data for the period of 1988-1989 to 2012-2013 were analyzed using time-series method called Autoregressive Integrated Moving Average (ARIMA) model and Regression analysis (curve estimation). In our study, the developed best ARIMA model for Tamil Nadu marine fish production was found to be ARIMA (1, 1, 1) which have the minimum BIC (Bayesian Information Criterion). ARIMA model had got a slightly higher forecasting accuracy rate for forecasting marine fish production of Tamil Nadu than Regression trend analysis. The independent sample test showed there was no significant difference between the two models. The limitations of ARIMA model include its requirement of a long time series data for better forecast. It is basically linear model assuming that data are stationary and have a limited ability to capture non-stationarities and nonlinearities in series data. Both the models indicated that Tamil Nadu marine fish production has plateaued and fishermen should be encouraged to adopt sustainable fishing practices.

Change in Fishing Patterns in Jammu & Kashmir Provinces of J&K – A Comparative Study

Jammu and Kashmir serves a congenial habitat for variety of fish species due to large number of cold water resources which has paved way for the development of fisheries sector in the state. The state has crossed 20.0 thousand tonnes of fish production because of modern aquacultural practices implied at both governmental and private levels. Kashmir province is a leading producer of fishes contributing more than 80% of the total production of the state while as Jammu on the other hand has also emerged as a major producer of animal protein through fisheries sector. The fish production data of four decades reflects increasing trend of production in all commercially important species of both the provinces. However the statistical models forecasting the future production provide an idea about the growth patterns in fishes. In this paper, growth pattern of three different fish species (Trout, Mirror carp and Country fish) from Kashmir province and various fishes from Jammu province (collectively named as Jammu fish) of the state was assessed using fish production data from 1956-57 to 2011-12. Forecasting of fish production was made on the basis of the best fitted statistical models. Results showed that Kashmir province shows overall compound growth of 4.2% against 7.9% of increased compound growth rate of fish production of Jammu province since 1956-57. Cubic model was found to be the best fitted model for all the species in both the regions. However, when future fish production of the state is taken into consideration, the statistical models indicated a decreasing trend in the overall fish production of both the provinces. Besides, the matter of concern is that the demand of 70,000 thousand tonne consumption of fish protein in the state which is a milestone yet to be achieved.

Sea-bob shrimp in Bahia state: aspects of their fishing and biology

The fishing activity Bahia presents great economic importance, being basically artisanal. Trawling is carried out since the 70’s, and among the resources exploited, the-bob-shrimp ( Xiphopeneus kroyeri ) is the most important. We analyzed data of its fisheries production (2001 and 2007), and presented aspects of their biology to the south coast (LS) and southernmost (LES). For assessment of fish production data were compiled from statistical bulletins CEPENE / IBAMA for the biological data used were generated between the years 2003/2005 and 2010/2011 for the coast of Ilheus (LS) and 2004/2009 for the RESEX (LES). The species represented half of shrimp harvested, although the composition was not homogeneous along the coast, which may represent up to 90% of the fisheries in the south coast and southern end. In Ilheus, there was a significant decline in mean CPUE between the first (2.60 ± 2.40 kg h-1) and the second period (0.73 ± 1.41 kg h-1), being the amount recorded in RESEX Corumbau about four times higher (9.96 ± 8.29 kg h-1). In both locations, the lowest catches occurred in the summer, with periods reproductive and recruitment continued. These results may be associated with different management strategies applied on both sites. We suggest that a standardized of landing data collection and a continuous monitoring by the responsible agencies are necessary; that the management policy and legislative currently in place should be reassessed and that new public policies that facilitate the management of this resource need to be developed.

Fish Farms at Sea: The Ground Truth from Google Earth

In the face of global overfishing of wild-caught seafood, ocean fish farming has augmented the supply of fresh fish to western markets and become one of the fastest growing global industries. Accurate reporting of quantities of wild-caught fish has been problematic and we questioned whether similar discrepancies in data exist in statistics for farmed fish production. In the Mediterranean Sea, ocean fish farming is prevalent and stationary cages can be seen off the coasts of 16 countries using satellite imagery available through Google Earth. Using this tool, we demonstrate here that a few trained scientists now have the capacity to ground truth farmed fish production data reported by the Mediterranean countries. With Google Earth, we could examine 91% of the Mediterranean coast and count 248 tuna cages (circular cages >40 m diameter) and 20,976 other fish cages within 10 km offshore, the majority of which were off Greece (49%) and Turkey (31%). Combining satellite imagery with assumptions about cage volume, fish density, harvest rates, and seasonal capacity, we make a conservative approximation of ocean-farmed finfish production for 16 Mediterranean countries. Our overall estimate of 225,736 t of farmed finfish (not including tuna) in the Mediterranean Sea in 2006 is only slightly more than the United Nations Food and Agriculture Organization reports. The results demonstrate the reliability of recent FAO farmed fish production statistics for the Mediterranean as well as the promise of Google Earth to collect and ground truth data.

Can the Liquid Live Micro‐Organisms System, a Commercial Probiotic, Affect Sediment, Water Quality, and Koi Carp Production in Fish Hatchery Ponds?

AbstractSediment and turbidity can reduce pond and effluent water quality and fish production. We investigated the efficacy of a commercial bacterial product, Liquid Live Micro‐Organisms (LLMO) System, in reducing sediment accumulation and improving water quality and fish production in hatchery ponds for 4.5 months. Four plastic‐lined ponds received LLMO treatment at a rate of 1 L per 63,230 L of pond water at 2‐week intervals throughout the study and additional twice‐weekly applications during the last 6 weeks of the study. Another four ponds were untreated and served as the control. All ponds were cleaned of bottom sediments, supplied with plastic containers (33–34 containers/ha) to collect sediment samples, filled with water, and managed to control Prymnesium parvum ichthyotoxicity. Koi (a variant of the common carp Cyprinus carpio) were stocked into ponds as fry and were fed a commercial diet. Turbidity, Secchi disk visibility, chlorophyll a, pH, ammonia‐nitrogen, suspended solids, carbonaceous biochemical oxygen demand, dissolved oxygen, and water temperature were monitored throughout the study. Sediment and fish production data were collected at the end of the study. Statistically, LLMO had no significant effect on sediment accumulation or any of the measured water quality variables and consequently had no effect on fish production. Our results did not support claims or reports that LLMO can reduce sediment accumulation or improve water quality and fish production. Two issues (small sample size and low LLMO application rate) may have confounded our results, thereby preventing us from making firm conclusions on the effects of LLMO on sediments, water quality, and fish production. We recommend that future studies be undertaken to address these issues.

Site selection and production performance of rainbow trout(Oncorhynchus mykiss)cage operations in small farm reservoirs: the Western Cape experience, South Africa

Cage farming of rainbow trout (Oncorhynchus mykiss) has expanded rapidly into private farm reservoirs of the Western Cape. During the grow-out season 2006, water quality problems such as increased mortality rates and off-flavour of the final product caused economic losses. To set criteria for improved site selection, water quality information of surface and near-bottom water was correlated with morphometric reservoir data, fish production data as well as the observed production difficulties. The data revealed good linkage between reservoir information and fish production data as well as production problems. The production problems correlated (P<0.01) with single water quality parameters so that suggestions for risk management indicators can be made. By ranking the data, threshold values for better production practice were determined. Thereafter, reservoirs of a minimum surface area of at least 3 ha would be recommended as well as reservoirs with good water exchange rates (>1 per year) to avoid oxygen problems. Reservoirs of larger surface area (>5 ha) produced significantly larger fish that grew faster and showed lower mortality rates.

Efficiency of African Catfish Clarias gariepinus in controlling unwanted reproduction of Nile Tilapia Oreochromis niloticus in low input production system

he present experiment was conducted in twelve earthen ponds 2100-m 2 at WorldFish Center research facility at Abbassa, Egypt, to assess the efficiency of African catfish (Clarias gariepinus) in controlling unwanted Nile tilapia (Oreochrmis niloticus) reproduction in grow out and to evaluate the performance of tilapia in polyculture system with catfish under low-input production system. Mixed sex tilapia fry (averaging 0.15 g total body weight) stocked at the rate of 2 fish/m 2 and African catfish fingerlings (223 g) were introduced two month later at stocking rates of 7 and 13% of tilapia into T2 and T3 respectively in addition to T1 which had no African catfish introduced to it. Ponds were fertilized weekly using chicken letter at the rate of 500 kg/ha. Water quality parameters were monitored weekly for measuring DO concentration, temperature, Secchi disk, pH and NH4. Also monthly water samples were taken for measuring pH, alkalinity, TAN, NO3, NO2 available phosphorus, chlorophyll a, and total hardness. Statistical analysis of the obtained fish production data at the end of the thirty-week experimental period, showed that catfish significantly (P< .05) reduced the biomass of recovered tilapia reproduction to 14.9 and 8 % fry as percentage of the total fish yield in T2 and T3, respectively as compared to 26.6% obtained in T1. Tilapia production in polyculture with catfish was significantly lower than tilapia monoculture while, on the other hand, total fish production was significantly (P< .05) higher in the case of both of the two polyculture treatments compared to the tilapia only treatment. The overall conclusion of the present experiment showed that under such stocking rate and production system, introduction of catfish at the rate of 13% of total Tilapia stocked has not only eliminated 70% of total Tilapia recruitment but also enhanced total pond production of marketable size fish in both of the polyculture treatments. T