TOOLBOXBROWSE TOPICS
RESOURCESABOUT THIS SITEpmwiki.org |
Agriculture, Natural Resource Management, and the Environment(a subtopic of Applications)
Expert Systems Developer Group, Penn State College of Agricultural Science. "The primary goal of the Expert Systems Developer Group (ESDG) is the development of expert systems to integrate the vast amount of information available in the agricultural sciences and make this information accessible for farm level decision making." The little black box for grain inspectors - A Canadian-made device could soon take the subjectivity and guesswork out of grading the quality of wheat. By Rebecca Dube. globeandmail.com (October 24, 2006). "For generations, grading grain has followed the same basic script: An inspector takes a sample of grain, looks it over, mentally compares it to all the grain he's seen before, and gives it a grade. ... DuPont Canada Inc., along with Agriculture Canada and several Canadian companies, has developed a new device that uses digital imaging and artificial neural networks to visually analyze and grade grain. It won't replace human grain inspectors, at least not in Canada, but DuPont hopes the technology will become a valuable tool around the globe. ... About Acurum - The old school: Grain inspector picks up a handful of grain, looks for signs of mildew, frost and other damage, and grades it on a scale of one to four. A new tool: The DuPont Acurum uses digital imaging and artificial intelligence to analyze and grade grain on a much more detailed level."
Taming the Tamarisk- A new GIS weapon helps a county fight a dangerous shrub. By Blake Harris. Government Technology (May 2005). "Growing from 5 to 20 feet tall, the tamarisk [also known as the salt cedar] was originally introduced into the United States from Eurasia in the early 1800s as an ornamental plant. Because of its dense, deep root system, settlers in Southwestern states planted salt cedar along streambeds to prevent erosion from flooding. Over the years, tamarisk spread from the Colorado River basin to New Mexico, and as far east as Texas. This proved disastrous for ecosystems in affected states, including Kansas. Kearny County, Kan., is fighting the spread of tamarisk along the Arkansas River with a combination of satellite imagery and GIS. ... At this point, the images go into a commercial software package -- Feature Analyst from Visual Learning Systems -- that uses machine learning technology to classify object-specific geographic features specified by the user. 'We actually go into the field with a submeter GPS unit, and we gather training samples and accuracy assessment samples for salt cedar,' [San Souci] said. 'Using these, we can train the computer to recognize salt cedar as opposed to other types of vegetation. And then finally, running those algorithms, it will spit out an ESRI Shapefile for the area that can be used in most GIS applications. Without these enhancement stages, you can't pull out salt cedar,' he continued. 'We tried, but it didn't work very well. There is a lot of confusion with all the other vegetation classes out there. But using these enhancements specific to salt cedar allows us to pull it out very precisely.'"
CORMS AI: Decision Support System for Monitoring US Maritime Environment. By Haleh Vafaie and Carl Cecere. 2005. In Proceedings of the Seventeenth Innovative Applications of Artificial Intelligence Conference, 1499 - . Menlo Park, Calif.: AAAI Press. "Rule based reasoning and case based reasoning have emerged as two important and complementary reasoning methodologies in artificial intelligence (Al). This paper describes the approach for the development of CORMS AI, a decision support system which employs rule-based and case-based reasoning to assist NOAA’s Center for Operational Oceanographic Products and Services watch standing personnel in monitoring the quality of marine environmental data and information. CORMS AI has been in operation since July 2003. The system accurately and reliably identifies suspect data and network disruptions, and has decreased the amount of time it takes to identify and troubleshoot sensor, network, and server failures. CORMS AI has proven to be robust, extendable, and cost effective. It is estimated that CORMS AI will save government over one million dollars per year when its full range of quality control monitoring capabilities is implemented." Machine vision aids animal management. By Jennifer Foreshew. Australian IT (August 21, 2007). "Australian researchers have developed a computerised system that uses Machine Vision Technology to help farmers manage domestic and wild animals on their properties. The system is capable of distinguishing between sheep, goats, cattle, horses, pigs, kangaroos and emus and can be used with other species. Machine vision is the ability of a computer to see. It uses cameras, analogue-to-digital conversion and digital signal processing. The data goes to a computer or robot controller. The project involves the University of Queensland, the University of Southern Queensland the federal government and RPM Rural Products. ... The system identifies animals and controls their movements via automated gates to access watering or feed points. It is expected to boost farmers' productivity and efficiency in remote areas and control loss of feed and water to feral animals."
I.T. May Help Clean a Polluted Sea, Say Researchers. By Mike Martin. NewsFactor Network (July 16, 2004). "'Rapid environmental changes call for continuous surveillance and online decision-making -- two areas where I.T. can be valuable,' say study authors Ioannis Athanasiadis and Pericles Mitkas. Both are computer science researchers at the Informatics and Telematics Institute Center for Research and Technology in Thessaloniki, Greece. In their study, entitled 'An Agent-Based Intelligent Environmental Monitoring System,' the researchers 'present a multi-agent system for monitoring and assessing air-quality attributes, which uses data coming from a meteorological station.' Their system, the study explains, uses a 'community of software agents to monitor and validate measurements coming from several sensors to assess air-quality.' ... Using agents to monitor the environment is a branch of 'enviromatics -- the research initiative examining the application of information technology in environmental research, monitoring, assessment, management and policy,' Athanasiadis explains. ... 'In O3RTAA, several software agents operate in a distributed-agent society in order to monitor both meteorological and air pollutants, to evaluate air quality and, ultimately, to trigger alarms' about environmental damage, Mitkas explains, adding that the system uses machine-learning algorithms and data-mining methodologies for 'extracting knowledge.'" Farming 2020 project at CSIRO's Autonomous Systems Laboratory: "CSIRO researchers are developing a system of tiny networked sensors, which are embedded around the farm and within the cattle themselves, to monitor -- and in some cases control – the herd's location, activity, health and well-being. The low-cost, low-power, networked sensors have the ability to communicate with each other, and to radio data back to a central server -- empowering the farmer with far more information about the status of the herd than ever before." Agriculture gains artificial intelligence. By Damian Clarkson. ITWeb (June 18, 2004). "The Agricultural Research Council - Institute for Soil Climate and Water (ARC-ISCW) has received two licences for an artificial intelligence (AI) application called RapAnalyst. The licences, valued at $100 000 (R640 000), were donated to the non-governmental organisation by Raptor Solutions Australasia, developer of RapAnalyst. The AI application transforms data relating to agricultural factors such as the weather and soil conditions into actionable, understandable information, says Raptor CEO Carl Wöcke. 'It's a free-thinking device. The main aim for us was to take AI technology and make it relevant to the business environment.'" Robots may scout fields on farms of the future. By Doug Peterson, University of Illinois Extension. @griculture Online (July 6, 2004) / also available from ACES News (U of I Creates Robot Farmers; July 6, 2004). "Farm equipment in the future might very well resemble the robot R2D2 of Star Wars fame. But instead of careening through a galaxy far, far away, these ag robots might be wobbling down a corn row, scouting for insects, blasting weeds and taking soil tests. University of Illinois agricultural engineers have developed several ag robots, one of which actually resembles R2D2, except that it's square instead of round. The robots are completely autonomous, directing themselves down corn rows, turning at the end and then moving down the next row, said Tony Grift, University of Illinois agricultural engineer. The long-term goal, he said, is for these small, inexpensive robots to take on some of the duties now performed by large, expensive farm equipment. ... Robots have been a part of industrial environments for decades now, but Grift said the time may be right for robots to adapt to the more rugged environment outdoors. His partner, [Yoshi] Nagasaka, has had considerable experience with ag robots, developing autonomous rice planters for the challenging landscape of rice paddies in Japan." Robots To Slash Farm Labour Costs. University of Warwick Media Centre (March 7, 2006). "The researchers from the University of Warwick's horticultural arm, Warwick HRI, and its manufacturing engineering section, Warwick Manufacturing Group, are working on a number of robotics and automation products that will vastly reduce the labour costs of farmers and growers. Those projects include: A robotic mushroom picker: the robot uses a charged coupled camera to spot and select only mushrooms of the exact size required for picking achieving levels of accuracy far in excess of human labour. ... Robot Grass Cutter ..." Big Ag Enlists Robots to Pick High-Hanging Fruit. By Eliza Strickland. Wired (June 21, 2007). "As if the debate over immigration and guest worker programs wasn't complicated enough, now a couple of robots are rolling into the middle of it. Vision Robotics, a San Diego company, is working on a pair of robots that would trundle through orchards plucking oranges, apples or other fruit from the trees. ... The two robots would work as a team: one an eagle-eyed scout, the other a metallic octopus with a gentle touch. The first robot will scan the tree and build a 3-D map of the location and size of each orange, calculating the best order in which to pick them. It sends that information to the second robot, a harvester that will pick the tree clean, following a planned sequence that keeps its eight long arms from bumping into each other." CLAES applications of expert systems to agriculture. Through the development, implementation and evaluation of knowledge based decision support systems, the Central Laboratory for Agricultural expert Systems is helping farmers through out Egypt optimize the use of resources and maximize food production. Links to descriptions of five different systems. What is a "Scarebot?" LSU Highlights (April 2002). "Aquatic farmers share a similar problem: the encroachment of predatory birds on their crops. In Louisiana, birds such as cormorants and pelicans are drawn to aquatic environments that provide a reliable feeding source of fish and crawfish. For this reason, the Louisiana aquaculture industry has suffered crop loss resulting in thousands of dollars in lost revenue. [Steve] Hall and [Randy] Price have developed a unique approach to the problem. 'Scarebot,' an autonomous robot designed to frighten birds from crop ponds, is a small, solar-powered boat that can run unattended for long periods of time, at speeds of 5-7 miles per hour." Robotic Farmer - Automated weeding could eventually reduce the use of herbicides. By Duncan Graham-Rowe. Technology Review (July 11, 2007). "Scientists in Denmark are developing an agricultural robot for identifying and eliminating weeds. While this might seem like a relatively easy task, it actually requires a lot of machine intelligence to pick out the weeds among the crops. The robot is still in the early stages of development, but the researchers hope that it will ultimately lead to a reduction in the amount of herbicides used by farmers and therefore cut costs. Called Hortibot, the semi-autonomous robot is a navigational platform designed to have different agricultural tools fitted to it to either mechanically remove weeds or precision-spray them with herbicide."
Farmers learning to grow the right crop in the right place - UT Ag group works to bring high-technology tools to farms. By Larisa Brass. Knoxville News-Sentinel (October 28, 2002). "At the University of Tennessee, John Wilkerson and his co-researchers in the Precision Agriculture Research and Education Group's sensors and controls lab test technologies available to farmers today and develop technologies for the future. ... Wilkerson said he's particularly excited about the work UT is doing with neural networks, or artificial intelligence, to help farmers better know their crops. The lab has developed prototypes of a technology that measures the wavelengths of light reflecting off a plant to 'learn' how much fertilizer particular plants, such as health or sick varieties, need. The farmer first introduces the device to different types of plants, inputting information about the plants and how much fertilizer should be dispensed in each case on a Palm-type device. Gradually the computer learns to discern each plant's need on its own. When the 'training' process is complete, the sensor would be attached to the front of a vehicle, with the nutrient dispenser on the back. As the computer 'sees' each plant, it communicates to the dispenser in the rear about which dose to dispense." Peanut Farmers Have a Suite Deal. Agricultural Research Magazine (October 2003; Volume 51, Number 10). "In the 1980s, peanut farmers noticed something puzzling: Their dryland fields were yielding more than their irrigated fields. Initially, they thought they were irrigating improperly or recording the irrigation amounts incorrectly. To find out, they asked scientists at the Agricultural Research Service's (ARS) National Peanut Research Laboratory (NPRL) in Dawson, Georgia, for help. ... From this collaboration, Irrigator Pro was developed. Irrigator Pro is a computerized expert system designed to manage peanut irrigation and pest control decisions. Irrigator Pro's goal is to improve economic returns from irrigation and reduce incidences of foreign material, immaturity, off-flavor, chemical residues, environmental harm, and aflatoxin. Over 20 years of scientific research data and information are incorporated in the software to help peanut farmers make informed, appropriate irrigation decisions. Little did anyone know that this was just the beginning of software systems that would help peanut farmers do their jobs. HarvPro, Peanut Curing Manager, Capital Investment Program, Sprinkler Cost Program, and later, WholeFarm followed." Farming from outer space - It is easier for a satellite in space to see whether a crop needs watering than for a farmer on the ground. By John Crace. The Guardian / Education Guardian (April 20, 2004). "'My vision is of a smart farm,' [Professor Graeme Wilkinson] says. 'The satellite images show what is needed and a robot fixes it." Development of a Decision Support System for Trumpeter Swan Management. From Richard Sojda, Wildlife Biologist Northern Rocky Mountain Science Center, Bozeman, MT. "The application of computer technologies for decision support systems in public land management, especially in relation to trumpeter swans, is my current research focus. This includes artificial intelligence, especially expert systems, cooperative distributed problem solving, geographic information systems, and modeling." Be sure to see the "slides from a presentation entitled, 'Using artificial intelligence in decision support for swan management' and the "slides from a presentation given at the Environmental Decision Support Systems and AI Workshop sponsored by the American Association for Artificial Intelligence in Orlando, FL, July 1999 entitled, 'Applying cooperative distributed problem solving methods trumpeter swan management.'" Flood Risk Management Research Consortium (FRMRC) launched by Environment Minister Elliot Morley and Environment Agency chair Sir John Harman. Department for Environment, Food and Rural Affairs (Defra) news release (April 7, 2004). "A new floods consortium staffed by some of Britain's leading engineers and scientists and launched today by Environment Minister Elliot Morley and Environment Agency chair Sir John Harman, will invest more than £5.5m to develop more accurate flood forecasting and warning and modelling systems and improve flood management infrastructure. Its work will help reduce risk to people, their property and the environment. The new group, known as the Flood Risk Management Research Consortium (FRMRC) will pull in staff from a number of universities to work with industrial partners and operational bodies on integrated research projects, including: ... Using intelligent systems, neural networks, fuzzy set theory, artificial intelligence evolution computation (genetic algorithms), decision support tools and expert systems - to help predict the likelihood of flooding." Subs newest aid in counting fish population. By Michelle Knott. New Scientist News Sevice / available from The Star (February 22, 2003). "A robot submarine that can be taught to recognize any fish species could soon be helping conservationists find out if fish populations really are as close to collapse as some suspect. ... Daniel Doolittle and his colleagues at the Virginia Institute of Marine Science in Gloucester Point, Va., have developed an autonomous underwater vehicle (AUV) that takes sonar pictures of passing fish shoals and uses an artificial intelligence system to recognize the fish species in question and count them. ... [H]e and his colleagues designed neural-network software that can be programmed to recognize any number of different species by their shape and the way they move. The neural network learns which combinations of inputs, such as shape details, lead to a particular output, such as a positive species identification. ...The U.S. navy is interested in the smart subs, which could be put to work patrolling harbours or shipping lanes on the lookout for mines or other weapons."  Be sure to see the General Index of AI in the news: Applications Reducing the cost of cotton production. By By Rob Hogan, Scott Stiles, Kelly Bryant, and James Marshall. Delta Farm Press (June 3, 2005). "Late-season insecticide sprays can be reduced by using the Bollman program. Cotman is a computer-based expert system developed by the University of Arkansas Division of Agriculture and contains Bollman as one of its components."
'Robot Tarzan' helps forest work - A fearless mobile robot is helping scientists monitor environmental changes in forests. By Jo Twist. BBC (December 29, 2003). "The hi-tech Tarzan of the robot world, nicknamed Treebot, is the first of its kind to combine networked sensors, a webcam, and a wireless net link. It is solar-powered and moves up and down special cables to take samples and measurements for vital analysis. Treebot has been developed by scientists at the US Centre for Embedded Network Sensing in California. ... Eighteen months in development, the main difference between Treebot and other fixed sensors is its autonomous nature and its ability to communicate with other devices and sensors." Man's best metallic friend - Robotic dogs sniff out toxins. By Stephen Singer. Associated Press / available from the Houston Chronicle (February 10, 2004). "They sniff, wag their tails, fetch and run in packs. But no one minds if these canines stick their noses into some pretty dirty stuff. That's because they are robotic dogs, modified by engineering students at Yale University to sniff out toxic materials."
"TheISIS lab [at Virginia Tech] was created in 1988 to investigate the application of artificial intelligence to agricultural and entomological problems."
CARMA, from the University of Wyoming Applied AI Lab. "CARMA is a case-based reasoning system that gives advice about the most economical responses to Wyoming grasshopper infestations based on roughly 140 combined years of entomologist expertise shared among eight experts in Wyoming. Tests have shown that CARMA's grasshopper forage consumption predictions, which are the core of determining the best course of action, very closely approximate the median predictions of the Wyoming experts. CARMA gives advice by comparing the current infestation to previous infestations (i.e., cases) and adapting the recommendations of the experts to fit the current infestation. Infestation probabilities for your location and the effectiveness of each treatment type are used to predict the future probabilities of re-infestation for each treatment type, and statistical methods are used to predict the range of economic benefits for each treatment option."
Data Management at the U.S. Department of the Interior's Office of Surface Mining (OSM). Expert System Method: "Significant advances have been made in recent years in applying artificial intelligence to the complicated engineering and scientific problems. Expert systems such as the one developed by OSM, utilize artificial intelligence. An expert system is comprised of a knowledge base and an inference engine. The knowledge base contains the accumulated knowledge of specialists in a narrowly defined area. The contents of the knowledge base are accessed and acted upon by the inference engine which generates heuristic solution strategies. Heuristic is an exploratory problem-solving strategy which can deal with inexact or incompletely formulated axioms or rules of thumb. Expert systems are capable of utilizing these rules of thumb to arrive at reasonable solutions to specific problems. OSM has developed a prototype expert system named Surface Mining And Reclamation Task Expert System Technology (SMARTEST). SMARTEST addresses the probable impacts from surface mining in the Appalachian Coal Basin. It contains a knowledge base derived from interviews with numerous hydrogeologists who are acknowledged to possess expertise both in the hydrogeology of the Appalachian Region and the hydrologic impacts of coal mining." Threatened Fauna Adviser. By Dr. Peter Gillard of the Department of Primary Industry Water and the Environment, Mt. Pleasant Laboratories, Tasmania and Dr. Sarah Munks of the Forest Practices Board, Tasmania. This story was also published in the September/October 1999 edition of PC AI magazine." Made available by Attar Software Limited. [Be sure to check out Attar's collection of case studies.]
Artificial Intelligence in Natural Resource Management. Homepage for Professor H. Randy Gimblett's course at the School of Renewable Natural Resources University of Arizona. As stated in the Fall 2002 syllabus: "The purpose of this course is to explore agent based modeling to aid in automating the decision making process to assist resource managers in making better decisions about human/landscape interactions in their subsequent environments." EXSEL is a forward chaining / decision support expert system designed to recommend the best mechanical and chemical range brush and weed control treatments in Texas. In addition, it also provides an analysis of prescription burn potential and will produce a pre-burn checklist. The user may select the plant kill efficacy level, force the system to consider certain types of treatments, or let the system choose the best alternative. From the Ranching Systems Group at the Center for Natural Resource Information Technology, Department of Rangeland Ecology and Management, Texas A&M University. Centre for Intelligent Environmental Systems. School of Computing, Staffordshire University. "The centre specialises in the application of artificial intelligence (AI) to problems affecting the natural environment. Projects to date have concentrated on the development of intelligent systems for the biological monitoring of river quality." Expert Systems, Decision Support Systems and Computer-Assisted Instruction for Water Resource Management(II). July 1993 - September 1995. 90 citations from AGRICOLA, by Diane Doyle, Water Quality Information Center of the National Agricultural Library, Agricultural Research Service, U.S. Department of Agriculture
BESAI: Binding Environmental Sciences and Artificial Intelligence. "BESAI is a mainly-European working group of Artificial Intelligence scientists and Environmental Science scientists who try to create an interdisciplinary knowledge for the solution of environmental problems and the development of better AI techniques." Workshop on Environmental Decision Support Systems (IJCAI-03 & EDSS'2003). "The workshop's central focus is the linkage between patterns of AI activity and the environment with a major emphasis on translating the scientific basis for environmental concern into techniques and strategies that address both the needs of human societies and the requirements of natural systems. The workshop will foster a discussion platform for AI and environmental science researchers." Vision and Remote Sensing: "Aerial views, from satellites or conventional aircraft, already provide a wealth of information. Machine vision can maximise the potential of these images, helping in the assessment of environmental change, enabling more efficient land use and providing geological infromation." Check out such interesting applications as Crop Classification in this collection fromThe British Machine Vision Association and Society for Pattern Recognition.
American Society of Agricultural and Biological Engineers (ASABE) Technical Library. Even though you can't access the full text, the article abstracts offer an exciting peek at applications such as:
John Deere - Field Robotics: "The focus of field robotics is to develop automation technologies that expand John Deere product capabilities. Field robotics involves the technologies that add automation capabilities to our products from the perspective of increasing productivity up to the goal of machine system autonomy. These technologies provide an integration of systems technologies including localization, control systems, sensing, drive-by-wire, artificial intelligence, tele-operation, semi-autonomous and fully autonomous operations."
More Readings"Computers and Electronics in Agriculture (COMPAG) provides international coverage of advances in the application of computer hardware, software and electronic instrumentation and control systems to agriculture, forestry and related industries." From Elsevier Science. Environmental Decision Support Systems and Artificial Intelligence. Papers from the 1999 AAAI Workshop. Ulises Corté and Miquel Sànchez-Marrè, Cochairs. Titles include: Recent Applications of Artificial Neural Networks in Forest Resource Management: An Overview; Intelligent Decision Support for Aerial Spray Deposition Management; and, A Multi-Paradigm Decision Support System to Improve Wastewater Treatment Plant Operation. Fuzzy Logic in Environmental Sciences: A Bibliography. "Domains of interest include: Agriculture, climatology, earthquakes, ecology, environmental sciences, fisheries, geography, geology, hydrology, meteorology, mining, natural resources, oceanography, petroleum, pollution, risk analysis, and rivers+lakes. ... We are preparing a chapter on fuzzy logic for a handbook in AI. The handbook is being assembled by AIRIES (Artificial Intelligence Research in Environmental Sciences). The book is intended to introduce environmental scientists to practical, state-of-the-art AI techniques. Many references were kindly given to us when we posted questions on newsgroups for the above-listed domains and on the met.ai newsgroup and fuzzy logic newsgroup. The AIRIES Fuzzy Team includes Rich Bankert, Mike Hadjimichael, and Bjarne Hansen." How to Pick an Orange? The choice between back-breaking human labor and efficient fruit-harvesting machines is approaching fast, just as it did more than 40 years ago when the mechanical tomato harvester revolutionized California agriculture. So why is there no easy answer to the question? By Karen Brandon. Los Angeles Times Magazine (January 2, 2005; subscription req'd.). "Part robot, part tractor, the contraption is an unusual combination of one internal-combustion engine, four rubber tires, eight digital cameras, eight electronic arms and an excruciating number of computer algorithms that choreograph every movement. Its metal arms maneuver among the branches, where 'eyes' spot the fruit and suction-cup 'hands' grasp them even more gently than human hands, which is what they are designed to replace. ... For now, this machine exists exclusively in a virtual citrus orchard on a computer screen in an unassuming second-story office in Sorrento Valley, San Diego's corridor of high-technology entrepreneurship. It was conceived by two Massachusetts Institute of Technology-educated inventers, Bret Wallach and Tony Koselka, who founded Vision Robotics Corp., a 4-year-old company whose most recent success was the invention of a robot vacuum cleaner capable of cleaning the carpet by itself while dodging table legs and other obstacles. ... Many agricultural researchers say machines may offer the best hope for many types of American agriculture that now depend on an immigrant workforce, subsidies and tariffs. Many believe machines offer a better, cheaper and possibly more humane way to harvest the labor-intensive crops that are the hallmark of farming in California, a nearly $28-billion industry. ... California --- the state with the nation's largest and most complicated agricultural labor market --- has been down the road to mechanization before, when the tomato harvester revolutionized production of that crop more than 40 years ago. But now, as then, the questions raised by the technology are rife with political, social and economic implications. ... César Chávez, quoting fearful farmworkers in a 1978 article in the Nation, called such machines 'los monstruos,' the monsters. ... Clearly, machine harvesting was a better way to get tomatoes out of the field. Not everyone, however, agreed that ought to be the only goal." |
