Rainfall, as one of the key components of hydrological cycle, plays an undeniable role for accurate modelling of other hydrological components. Therefore, a precise forecasting of annual rainfall is ...of the high importance. In this regard, several studies have been tried to predict annual rainfall of different climate zones using machine learning and soft computing algorithms. This study investigates the application of an innovative hybrid method, namely Multilayer Perceptron-Whale Optimization Algorithm (MLP-WOA) to predict annual rainfall comparatively to the ordinary Multilayer Perceptron models (MLP). The models were developed by using 3-Input variables of annual rainfall at lag1, 2 and 3 corresponding to P
t-1
, P
t-2
and P
t-3,
respectively of two synoptic stations of Senegal (Fatick and Goudiry) in the time period of 1933–2013. 75% of the dataset were utilized for training and the other 25% for testing the studied models Accurateness of the mentioned models was examined using root mean squared error, correlation coefficient, and KlingGupta efficiency. Results showed that MLP-WOA3 and MLP3 using both P
t-1
, P
t-2
and P
t-3
as inputs presented the most accurate forecasting in Fatick and Goudiry stations, respectively. In Fatick station, MLP-WOA3 decreased the RMSE value of MLP3 by 18.3% and increased the R and KGE values by 3.0% and 130%, respectively in testing period. But, in Goudiry station, MLP-WOA3 increased the RMSE value of MLP3 by 3.9% and increased the R and KGE values by 10.2% and 91% in testing period. Therefore, it can be realized that the MLP-WOA3 could not able to reduce the RMSE value of correspondent MLP model in Goudiry station. The conclusive results indicated that MLP-WOA slightly improved the accuracy of correspondent MLP models and may be recommended for annual rainfall forecasting.
Sequential pattern mining has been introduced by Agrawal and Srikant (in: Proceedings of ICDE’95, pp 3–14, 1995) 2 decades ago, and its usefulness has been widely proved for different mining tasks ...and application fields such as web usage mining, text mining, bioinformatics, fraud detection and so on. Since 1995, despite numerous optimization proposals, sequential pattern mining remains a costly task that often generates too many patterns. This limit, also reached by itemset mining, was circumvented by pattern sampling. Pattern sampling is a non-exhaustive method for instantly discovering relevant patterns that ensures a good interactivity while providing strong statistical guarantees due to its random nature. Curiously, such an approach investigated for different kinds of patterns including itemsets and subgraphs has not yet been applied to sequential patterns. In this paper, we propose the first method dedicated to sequential pattern sampling. In addition to address sequential data, the originality of our approach is to introduce a class of interestingness measures relying on the norm of the sequence, named
norm-based utilities
. In particular, it enables to add constraints on the norm of sampled patterns to control the length of the drawn patterns and to avoid the pitfall of the “long tail” where the rarest patterns flood the user. We propose a new two-step random procedure integrating this class of measures, named
NUSS
A
M
P
L
I
N
G
that randomly draws sequential patterns according to frequency weighted by a norm-based utility. We demonstrate that this method performs an exact sampling according to the underlying measure. Moreover, despite the use of rejection sampling, the experimental study shows that
NUSS
A
M
P
L
I
N
G
remains efficient. We especially focus on the interest of norm constraints and exponential decays that help to draw general patterns of the “head”. We also illustrate how to benefit from these sampled patterns to instantly build an associative classifier dedicated to sequences. This classification approach rivals state-of-the-art proposals showing the interest of sequential pattern sampling with norm-based utility.
We consider the structural change in a class of discrete valued time series, which the conditional distribution belongs to the one‐parameter exponential family. We propose a change point test based ...on the maximum likelihood estimator of the model's parameter. Under the null hypothesis (of no change), the test statistic converges to a well‐known distribution, allowing the calculation of the critical value of the test. The test statistic diverges to infinity under the alternative, meaning that the test has asymptotic power one. Some simulation results and real data applications are reported to show the effectiveness of the proposed procedure.
Recently, a new approach to extension and climate information services, namely Participatory Integrated Climate Services for Agriculture (PICSA) has been developed. PICSA makes use of historical ...climate records, participatory decision-making tools and forecasts to help farmers identify and better plan livelihood options that are suited to local climate features and farmers’ own circumstances. This approach was implemented in 2016 in two sites in Senegal and Mali, with 57 and 47 farmers, respectively. At the end of the growing season, these farmers were surveyed to explore their perceptions on the use of the approach. In Senegal and Mali, respectively 97% and 76% of the respondents found the approach ‘very useful’. The approach enabled farmers to make strategic plans long before the season, based on their improved knowledge of local climate features. Moreover, evidence demonstrates that PICSA stimulated farmers to consider and then implement a range of innovations which included: (i) changes in timing of activities such as sowing dates, (ii) implementing soil and water management practices, (iii) selection of crop varieties, (iv) fertiliser management and (v) adaptation of plans for the season (farm size, etc.) to the actual resources available to them. The study also demonstrated the potential of farmer-to-farmer extension in scaling up the approach, which is of great interest especially in the current context of limited extension services in the West African region. Keywords: Climate change, Climate information services, Climate variability, Food security, Livelihood options, West Africa
The determination of scour characteristics in the downstream of sluice gate is highly important for designing and protection of hydraulic structure. The applicability of modern data-intelligence ...technique known as extreme learning machine (ELM) to simulate scour characteristics has been examined in this study. Three major characteristics of scour hole in the downstream of a sluice gate, namely the length of scour hole (Ls), the maximum scour depth (Ds), and the position of maximum scour depth (Lsm), are modeled using different properties of the flow and bed material. The obtained results using ELM were compared with multivariate adaptive regression spline (MARS). The dimensional analysis technique was used to reduce the number of input variable to a smaller number of dimensionless groups and both the dimensional and non-dimensional variables were used to model the scour characteristics. The prediction performances of the developed models were examined using several statistical metrics. The results revealed that ELM can predict scour properties with much higher accuracy compared to MARS. The errors in prediction can be reduced in the range of 79%–81% using ELM models compared to MARS models. Better performance of the models was observed when dimensional variables were used as input. The result indicates that the use of ELM with non-dimensional data can provide high accuracy in modeling complex hydrological problems.
Analyzing trends of annual rainfall and assessing the impacts of these trends on the hydrological regime are crucial in the context of climate change and increasing water use. This research ...investigates the recent trend of hydroclimatic variables in the Senegal River basin based on 36 rain gauge stations and three hydrometric stations not influenced by hydraulic structures. The Man Kendall and Pettitt’s tests were applied for the annual rainfall time series from 1940 to 2013 to detect the shift and the general trend of the annual rainfall. In addition, trends of average annual flow rate (AAFR), maximum daily flow (MADF), and low flow rate (LFR) were evaluated before and after annual rainfall shift. The results show that the first shift is situated on average at 1969 whereas the second one is at 1994. While the first shift is very consistent between stations (between 1966 and 1972), there is a significant dispersion of the second change-point between 1984 and 2002. After the second shift (1994), an increase of annual rainfall is noticed compared to the previous period (1969–1994) which indicates a not significant, partial rainfall recovery at the basin level. The relative changes of hydrologic variables differ based on the variables and the sub-basin. Relative changes before and after first change-point are significantly negative for all variables. The highest relative changes are observed for the AAFR. Considering the periods before and second shifts, the relative changes are mainly significantly positive except for the LFR.
Accurate monitoring of surface water bodies is essential in numerous hydrological and agricultural applications. Combining imagery from multiple sensors can improve long-term monitoring; however, the ...benefits derived from each sensor and the methods to automate long-term water mapping must be better understood across varying periods and in heterogeneous water environments. All available observations from Landsat 7, Landsat 8, Sentinel-2 and MODIS over 1999–2019 are processed in Google Earth Engines to evaluate and compare the benefits of single and multi-sensor approaches in long-term water monitoring of temporary water bodies, against extensive ground truth data from the Senegal River floodplain. Otsu automatic thresholding is compared with default thresholds and site-specific calibrated thresholds to improve Modified Normalized Difference Water Index (MNDWI) classification accuracy. Otsu thresholding leads to the lowest Root Mean Squared Error (RMSE) and high overall accuracies on selected Sentinel-2 and Landsat 8 images, but performance declines when applied to long-term monitoring compared to default or site-specific thresholds. On MODIS imagery, calibrated thresholds are crucial to improve classification in heterogeneous water environments, and results highlight excellent accuracies even in small (19 km2) water bodies despite the 500 m spatial resolution. Over 1999–2019, MODIS observations reduce average daily RMSE by 48% compared to the full Landsat 7 and 8 archive and by 51% compared to the published Global Surface Water datasets. Results reveal the need to integrate coarser MODIS observations in regional and global long-term surface water datasets, to accurately capture flood dynamics, overlooked by the full Landsat time series before 2013. From 2013, the Landsat 7 and Landsat 8 constellation becomes sufficient, and integrating MODIS observations degrades performance marginally. Combining Landsat and Sentinel-2 yields modest improvements after 2015. These results have important implications to guide the development of multi-sensor products and for applications across large wetlands and floodplains.
This research investigated the effect of climate change on the two main river basins of Senegal in West Africa: the Senegal and Gambia River Basins. We used downscaled projected future rainfall and ...potential evapotranspiration based on projected temperature from six General Circulation Models (CanESM2, CNRM, CSIRO, HadGEM2-CC, HadGEM2-ES, and MIROC5) and two scenarios (RCP4.5 and RCP8.5) to force the GR4J model. The GR4J model was calibrated and validated using observed daily rainfall, potential evapotranspiration from observed daily temperature, and streamflow data. For the cross-validation, two periods for each river basin were considered: 1961–1982 and 1983–2004 for the Senegal River Basin at Bafing Makana, and 1969–1985 and 1986–2000 for the Gambia River Basin at Mako. Model efficiency is evaluated using a multi-criteria function (Fagg) which aggregates Nash and Sutcliffe criteria, cumulative volume error, and mean volume error. Alternating periods of simulation for calibration and validation were used. This process allows us to choose the parameters that best reflect the rainfall-runoff relationship. Once the model was calibrated and validated, we simulated streamflow at Bafing Makana and Mako stations in the near future at a daily scale. The characteristic flow rates were calculated to evaluate their possible evolution under the projected climate scenarios at the 2050 horizon. For the near future (2050 horizon), compared to the 1971–2000 reference period, results showed that for both river basins, multi-model ensemble predicted a decrease of annual streamflow from 8% (Senegal River Basin) to 22% (Gambia River Basin) under the RCP4.5 scenario. Under the RCP8.5 scenario, the decrease is more pronounced: 16% (Senegal River Basin) and 26% (Gambia River Basin). The Gambia River Basin will be more affected by the climate change.
The objectives of this study were to investigate water saving strategies in the paddy field and to evaluate the performance of some of the newly released rice varieties. Field experiments were ...conducted at Fanaye in the Senegal River Valley during two rice growing seasons in 2015. Three irrigation regimes ((i) continuous flooding, (ii) trigging irrigation at soil matric potential (SMP) of 30 kPa, (iii) trigging irrigation at SMP of 60 kPa) were tested in an irrigated lowland rice field. Irrigation regimes (ii) and (iii) are alternate wetting and drying (AWD) cycles. Four inbred rice varieties (NERICA S-21, NERICA S-44, Sahel 210 and Sahel 222) and one hybrid rice (Hybrid AR032H) were evaluated under five nitrogen fertilizer rates (0, 50, 100, 150 and 200 kg N ha−1). The results showed that rice yield varied from 0.9 to 12 t ha−1. The maximum yield of 12 t ha−1 was achieved by NERICA S-21 under AWD 30 kPa at 150 kg N ha−1. The AWD irrigation management at 30 kPa resulted in increasing rice yield, rice water use and nitrogen use efficiency and reducing the irrigation applications by 27.3% in comparison with continuous flooding. AWD30 kPa could be adopted as a water saving technology for water productivity under paddy production in the Senegal River Middle Valley. Additional research should be conducted in the upper Valley, where soils are sandier and water is less available, for the sustainability and the adoption of the irrigation water saving practices across the entire Senegal River Valley.
Understanding evapotranspiration and its long-term trends is essential for water cycle studies, modeling and for water uses. Spatial and temporal analysis of evapotranspiration is therefore important ...for the management of water resources, particularly in the context of climate change. The objective of this study is to analyze the trend of reference evapotranspiration (ET0) as well as its sensitivity to climatic variables in the Senegal River basin. Mann-Kendall’s test and Sen’s slope were used to detect trends and amplitude changes in ET0 and climatic variables that most influence ET0. Results show a significant increase in annual ET0 for 32% of the watershed area over the 1984–2017 period. A significant decrease in annual ET0 is observed for less than 1% of the basin area, mainly in the Sahelian zone. On a seasonal scale, ET0 increases significantly for 32% of the basin area during the dry season and decreases significantly for 4% of the basin during the rainy season. Annual maximum, minimum temperatures and relative humidity increase significantly for 68%, 81% and 37% of the basin, respectively. However, a significant decrease in wind speed is noted in the Sahelian part of the basin. The wind speed decrease and relative humidity increase lead to the decrease in ET0 and highlight a “paradox of evaporation” in the Sahelian part of the Senegal River basin. Sensitivity analysis reveals that, in the Senegal River basin, ET0 is more sensitive to relative humidity, maximum temperature and solar radiation.