A Comparison of Machine Learning Techniques for Modeling River Flow Time Series: The Case of Upper Cauvery River Basin

Models of river flow time series are essential in efficient management of a river basin. It helps policy makers in developing efficient water utilization strategies to maximize the utility of scarce water resource. Time series analysis has been used extensively for modeling river flow data. The use of machine learning techniques such as support-vector regression and neural network models is gaining increasing popularity. In this paper we compare the performance of these techniques by applying it to a long-term time-series data of the inflows into the Krishnaraja Sagar reservoir (KRS) from three tributaries of the river Cauvery. In this study flow data over a period of 30 years from three different observation points established in upper Cauvery river sub-basin is analyzed to estimate their contribution to KRS. Specifically, ANN model uses a multi-layer feed forward network trained with a back-propagation algorithm and support vector regression with epsilon intensive-loss function is used. Auto-regressive moving average models are also applied to the same data. The performance of different techniques is compared using performance metrics such as root mean squared error (RMSE), correlation, normalized root mean squared error (NRMSE) and Nash-Sutcliffe Efficiency (NSE).

Springsheds of the Santa Fe River Basin

Powerpoint presentation (PDF has 45 pages.)

Evaluation of salmon and steelhead spawning habitat quality in the South Fork Trinity River Basin, 1997

Sediment sampling was used to evaluate chinook salmon (Oncorhynchus tshawytscha) and steelhead (O. mykiss) spawning habitat quality in the South Fork Trinity River (SFTR) basin. Sediment samples were collected using a McNeil-type sampler and wet sieved through a series of Tyler screens (25.00 mm, 12.50 mm, 6.30 mm, 3.35 mm, 1.00 mm, and 0.85 mm). Fines (particles < 0.85 mm) were determined after a l0-minute settling period in Imhoff cones. Thirteen stations were sampled in the SFTR basin: five stations were located in mainstem SFTR between rk 2.1 and 118.5, 2 stations each were located in EF of the SFTR, Grouse Creek, and Madden Creek, and one station each was located in Eltapom and Hayfork Creeks. Sample means for fines(particles < 0.85 mm) fer SFTR stations ranged between 14.4 and 19.4%; tributary station sample mean fines ranged between 3.4 and 19.4%. Decreased egg survival would be expected at 4 of 5 mainstem SFTR stations and at one station in EF of SFTR and Grouse Creek where fines content exceed 15%. Small gravel/sand content measured at all stations were high, and exceed levels associated with reduced sac fry emergence rates. Reduction of egg survival or sac fry emergence due to sedimentation in spawning gravels could lead to reduced juvenile production from the South Fork Trinity River. (PDF contains 18 pages.)

Harnessing the fishery potential of man-made lakes for the partial commercialisation of Niger River Basin Development Authority, Minna, Nigeria

Niger River Basin Development Authority Minna (NRBDA) is one of the eleven river basins in Nigeria now undergoing transition towards partial commercialisation. In the light of this the need to be self-sustaining through exploration and exploitation of every possible areas along their operation to yield revenue cannot be over-emphasized. Therefore it is most pertinent to consider fisheries activities along their water bodies as one of the major sources of revenue by organising the local fishermen operating along the water into cooperative bodies and made to pay for fishing rights. Strategies to accomplish this objective is highlighted. The need to embark on aquaculture projects by construction of fish ponds at suitable sites along the reservoirs and developing the recreational potentials of their water bodies as sources of revenue is also stressed

The Permanent Okavango River Basin Water Commission annual report 2009

First published annual report of OKACOM, covering first period of Sida-funded three year workplan from 2007 until 2009, during which the Secretariat was established. (PDF contains 32 pages)

Economic incentives for water resource management in the Pak Phanang river basin of southern Thailand

The study examines the existing water allocation methods and other policies that provide constraints or incentives for the most efficient use of water resources. Given the production condition of the local people, and the technical and physical attributes of water resources, the principal hypothesis of this study is that the benefits obtained from fresh water resources in the study area can be improved through better resource management.

Flux and sources of nutrients in the Mississippi-Atchafalaya River Basin: Topic 3 Report for the Integrated Assessment on Hypoxia in the Gulf of Mexico.

Ths report addresses the following two questions: 1) What are the loads (flux) of nutrients transported from the Mississippi-Atchafalaya River Basin to the Gulf of Mexico, and where do they come from within the basin? 2) What is the relative importance of specific human activities, such as agriculture, point-source discharges, and atmospheric deposition in contributing to these loads? These questions were addressed by first estimating the flux of nutrients from the Mississippi-Atchafalaya River Basin and about 50 interior basins in the Mississippi River system using measured historical streamflow and water quality data. Annual nutrient inputs and outputs to each basin were estimated using data from the National Agricultural Statistics Service, National Atmospheric Deposition Program, and point-source data provided by the USEPA. Next, a nitrogen mass balance was developed using agricultural statistics, estimates of nutrient cycling in agricultural systems, and a geographic information system. Finally, multiple regression models were developed to estimate the relative contributions of the major input sources to the flux of nitrogen and phosphorus to the Gulf of Mexico.

Modeling the effect of snow on seasonal runoff within the Truckee River drainage basin

EXTRACT (SEE PDF FOR FULL ABSTRACT): We estimate monthly runoff for a 2-dimensional solution domain containing those areas tributary to Pyramid Lake, Nevada (the Truckee River drainage basin) at a 1-kilometer grid cell spacing. ... To calculate the effect of snow on the hydrologic system, we perform two experiments. In the first we assume that all precipitation falls as rain; in the second we assume that some precipitation falls as snow, thus available water is a combination of rain and snowmelt. We find that considering the effect of snow results in a more accurate representation of mean monthly flow rates, in particular the peak flow during the melt season in the Sierra Nevada. These preliminary results indicate that a relatively simple snow model can improve the representation of Truckee River basin hydrology, significantly reducing errors in modeled seasonal runoff.

A New Species of the Genus Garra from Nujiang River Basin, Yunnan, China (Teleostei: Cyprinidae)

2003年4月,于怒江二级支流镇康县境内的大叉河中采获一批墨头鱼属(Garra)鱼类标本,经鉴定为一新种,命名为怒江墨头鱼(G.nujiangensis Chen and Yang,sp.nov.).该新种主要鉴别特征:围尾柄鳞12～14:侧线鳞48～50:在小个体中有一对微小的吻须;背鳍分支鳍条8～9;侧线上鳞5～6,侧线下鳞3～4;体高小于头长;臀鳍起点处的小于眼后至吻端的距离;腹鳍前长为体长的50.0%～53.7%;肛门前长为体长的58.9%～63.9%:体宽为体长的16.7%～19.6%:体高为体长的19.2%～22.6%.本研究证实,在缺须的墨头鱼属的一些物种中,如高体墨头鱼(G.alticorpora)和怒江墨头鱼(G.nujiangensis),其幼体中往往具有一对很小的吻须.

SPECIES DIVERSITY DYNAMICS OF FRAGMENTED TROPICAL RAINFORESTS IN THE LOWER-LANCANG/ UPPER-MEKONG RIVER BASIN

　在澜沧江下游/ 湄公河上游的滇南西双版纳地区,通过样方法比较了热带雨林的连片与3 个小片断的物 种多样性变化趋势。与连续森林比较,片断热带雨林的植物物种丰富度和物种多样性指数都比较低,而且有相当低 比例的大高位芽、中高位芽和附生等生活型植物,而藤本、小高位芽和矮高位芽等生活型植物的比例则较高;泛热 带、热带亚洲至热带非洲的区系成分比例较高,而当地成分则减少;群落的上层树木比下层树木更加稳定。同样,动 物的物种多样性指数和均衡度在片断热带雨林中都较低,与其密切相关的是片断热带雨林的环境质量,而不是片 断的大小。此外,也探讨了片断热带雨林物种变化与森林小气候的关系,阐明了由凉湿向干暖转化的“林内效应"是 其物种变化的重要原因之一。

Garra rotundinasus, a new species of cyprinid fish (Pisces : Teleostei) from the upper Irrawaddy River basin, China

Garra rotundinasus, a new cyprinid species from the upper Irrawaddy River basin in Yunnan, China, is herein described. It shares with G. gravelyi the presence of a snout having a poorly developed proboscis represented by a truncate area in front of the nostrils, a character distinguishing both from all other Southeast Asian and Chinese congeners. The two species are distinct in coloration, morphometric and meristic characters. The sympatrically occurring G. tengchongensis is very similar to G. rotundinasus in possessing 36-37 perforated lateral line scales, 5 or 6 scales between the anus and anal-fin origin, and an anterior position of the anus (anus to anal distance 32.1-51.8% of pelvic to anal distance). Garra rotundinasus can be differentiated from G. tengehongensis in having a more slender caudal peduncle, a larger disc and no dark central band on the dorsal fin.

Fixation of the type species of the genus Sinilabeo and description of a new species from the upper Yangtze river basin, China (Pisces : Cyprinidae)

The type species of the cyprinid genus Sinilabeo was misidentified as Varicorhinus tungting, and the species under the generic name belong to Bangana and Linichthys. In order to make Sinilabeo available, its type species is fixed under Article 70.3.2 of the 1999 edition of the International Code of Zoological Nomenclature as S. hummeli, a new species herein described from the upper Yangtze River basin in Chongqing City and Sichuan Province, South China. A re-definition is provided for Sinilabeo. It resembles Qianlabeo in having an upper lip only present in the side of the upper jaw and uncovered by the rostral fold, but missing in the median part of the upper jaw that, instead, bears a thin, flexible, and cornified sheath, covered by the rostral fold, a character that can separate both from all other existing genera of Asian labeonins. However, Sinilabeo is distinguished from Qianlabeo in the presence of a rostral fold disconnected from the lower lip; a broadly interrupted postlabial groove only restricted to the side of the lower jaw; an upper lip, which is only present in the side of the upper separated from it by a groove; 9-10 branched dorsal-fin rays; two pairs of tiny maxillary barbels.