Search Documents

By Jack D. Melin

The commercial development of the Liwell Screen is a result of a thorough search for a non-blinding and highly efficient screening device capable of handling even the most difficult-to- screen feed materials. A proprietary development of Hein, Lehmann A.G. of Duesseldorf, West Germany, the Liwell Screen utilizes a unique flexible deck motion for sizing a variety of sticky, high surface moisture feed materials including raw coal and lignite at separations ranging from 3/4-inches (19mm) down to 10 mesh (1.5 mm).

Jan 1, 1983

By C. D. Anderson

A variety of processing technologies exist for recovery from both primary and secondary sources of rhenium. Currently, there are no known primary rhenium deposits; thus, the method in which primary rhenium is produced is dependent on the commodity of which it is a byproduct, e.g., copper, molybdenum, uranium, etc. In addition, focus on the recovery of rhenium from secondary sources, such as alloy scraps and catalysts, is continually growing. This paper presents a review of both primary and secondary processing technologies for the recovery of rhenium.

By Dolf W. Fieldman

Most recently the geologic setting of the mineral deposits in the Silver Cliff district is described by William M. Sharp in ?Geologic Map of the Silver Cliff and Rosita Volcanic Centers, Custer County, Colorado?, (U. S. G. S. Map I- 1081). The discussion will relate only to the southern half of the Silver Cliff volcanic center and differences in geologic interpretation, which are largely structural, will be pointed out as they arise. Only the manganese/silver zone of the Kate Area will be discussed in detail.

Jan 1, 1980

By K. Taniguchi, Y. Inada

When underground openings are excavated in rock mass for storage of Liquefied Natural Gas, hereinafter referred to as L.N.G., as its temperature is -162o C, steep temperature gradients and thermal stress occur around the openings. That is, the plastic zone and cracks around openings will expand with time. In this paper, the range of cracks which were obtained by the Crack Analysis Method and the range of the plastic zone which was obtained by the No Tension Analysis Method were investigated and compared.

Jan 1, 1986

By John Hayden

The nation runs on energy. It is essential for the economic growth and national security of the United States that the nation has an adequate, sustainable, environmentally acceptable and economically viable balanced supply of energy sources, (e.g., coal, petroleum, nuclear, natural gas, solar, wind, geothermal, biomass, hydroelectric power). Therefore, the allocation of mineral raw materials to the energy-producing sector of the economy must be a top priority that requires the total demand for energy-related materials be judged in terms of domestic supply (Fig. 1).

Jan 1, 2012

By W. M. Ma, Daniel W. H. Su, K. Centofanti, Yi Luo, W. L. Zhong, Syd S. Peng

7.1 INTRODUCTION Subsidence measurements include surveys of surface and sub- surface movements and measurements and monitoring of surface structural damages. In this chapter the most commonly employed methods are discussed. 7.2 MEASUREMENT OF SURFACE MOVEMENT Surface movements involve two basic components, subsidence and displacement. The other five components (i.e., slope, curvature, strain, twisting, and shearing) are derived from the two basic components. Since all measurements are geometrical, they can be measured by common surveying techniques. 7.2.1 MONUMENTS The first step is to select the types of monuments or surveying stations. Various types of monuments have been employed. The simplest one is a paint mark on the pavement or concrete slab, although this should be discouraged because it is easily affected by artificial or environmental factors. Others use steel or wooden rods, 2 to 3 in. in diameter or square by 2 to 5 ft long, driven all the way down, flush with the ground. Both types of-monuments have no provision for frozen ground heave and both are tampered with easily. A more elaborate type is shown in Fig. 7.1 (O'Rourke et al., 1982). A rebar or iron pipe, 2 in. in diameter by 6 ft long is driven down to nearly flush with ground surface. The top 4-ft section of the hole around the pipe is enlarged to 1 ft in diameter and grouted with concrete. The most sophisticated type of monument is shown in Fig. 7.2 (Conroy and Gyannaty, 1983a). It consists of two hollow steel pipes. The inner I-in. pipe, 10 ft. long is enclosed by a 2-in. pipe at the upper 5-ft. interval. The gap between pipes is filled with foam to isolate the inner pipe from external environmental effects. The bottom of the inner pipe can either remain open or be sealed with a cap, depending on whether the ground is dry or wet. 7.2.2 MONUMENT ARRANGEMENT AND SURVEY LINES The monuments are installed strategically to form survey lines. Three basic types of monument arrangements are shown in Fig. 7.3. Figs. 7.3a and 7.3b are for single and multiple panels respectively; Fig. 7.3~ is mainly for research purposes with multiple survey lines both in longitudinal and transverse directions. This is extremely useful for defining the distributions of ground deformation, as shown in Figs. 2.10 and 2.11. Basically there are two types of survey lines: the whole basin survey line which extends across the panel width or length (e.g., lines R, R, in Fig. 7.3 a&b), and the half basin survey line which covers approximately half of the panel width or length (e.g., lines R, F in Fig. 7.3 &b). Survey lines are generally straight and linear. They should be located on the major crosssections of the subsidence basin. Survey lines must extend beyond the edge of the opening for a sufficient distance so that the edges of the subsidence basin can be determined accurately. The minimum distance from the edge of the opening must be [ ] where h = mining depth, [ ] = angle of draw, and [ ] = 5 to 7 times monument spacing for whole basin surveys, or 8 to 10 times the monument spacing for half basin surveys. There must be at least two controlling monuments at each end of each survey line. Controlling monuments must be located beyond the influence of underground mining. The spacing of the monuments ranges from 15 to 200 ft. The UK National Coal Board (NCB, 1975) recommended a spacing equivalent to 0.20 of the mining depth. Peng and Geng (1982) recommended that the maximum monument spacing be dependent on mining depths as follows:

Jan 1, 1992

By Soner Top

In this study, a process to separate manganese and iron from manganiferous iron ores by reductive acid leaching followed by magnetic separation was conceived and experimentally tested. In the leaching process, sulfuric acid was used as lixiviant and oxalic acid was used as reductant. The experimental results showed that the manganese and iron separation was optimum when the concentration of the sulfuric acid and oxalic acid were 0.75 M and 30 g/L, respectively, at a temperature of 80 °C, a solid/ liquid ratio of 67 g/L, stirring speed of 400 rpm, and leaching duration of 60 min. Under this condition, 90.49% and 6.78% of Mn and Fe were dissolved, respectively, from the ore sample with a size fraction of − 106 μm. It was determined that the leaching of manganese from the ores was a second-order reaction with an activation energy (Ea) of 53.38 kJ/mol. The leaching residues obtained under the optimum condition were subjected to high-intensity wet magnetic separation tests to recover the remaining iron content. This separation process produced a concentrate containing 56.20% Fe and 1.79% Mn with iron and manganese recoveries of 56.83% and 66.73%, respectively. A magnetic separation test from an unleached ore sample was also carried out as a benchmark. To the best of our knowledge, this is the first time that a magnetic separation process was used to a residue obtained from reductive acid leaching of manganiferous iron ores to recover iron.

By Soner Top

In this study, a process to separate manganese and iron from manganiferous iron ores by reductive acid leaching followed by magnetic separation was conceived and experimentally tested. In the leaching process, sulfuric acid was used as lixiviant and oxalic acid was used as reductant. The experimental results showed that the manganese and iron separation was optimum when the concentration of the sulfuric acid and oxalic acid were 0.75 M and 30 g/L, respectively, at a temperature of 80 °C, a solid/ liquid ratio of 67 g/L, stirring speed of 400 rpm, and leaching duration of 60 min. Under this condition, 90.49% and 6.78% of Mn and Fe were dissolved, respectively, from the ore sample with a size fraction of − 106 μm. It was determined that the leaching of manganese from the ores was a second-order reaction with an activation energy (Ea) of 53.38 kJ/mol. The leaching residues obtained under the optimum condition were subjected to high-intensity wet magnetic separation tests to recover the remaining iron content. This separation process produced a concentrate containing 56.20% Fe and 1.79% Mn with iron and manganese recoveries of 56.83% and 66.73%, respectively. A magnetic separation test from an unleached ore sample was also carried out as a benchmark. To the best of our knowledge, this is the first time that a magnetic separation process was used to a residue obtained from reductive acid leaching of manganiferous iron ores to recover iron.

By Hamid Mazouz, Mohammed Hakkar, Rim Jouraiphy, Fatima Ezzahra Arhouni, Ahmed Mahrou, Aziz Boukhair, Mohammed Fahad

The wet process is the most commonly used worldwide for phosphoric acid (PA) production, in which phosphate rock (PR) is reacted with strong acid mainly sulfuric acid. This work aims on studying the rare earth elements (REEs) distribution during the production of phosphoric acid using different qualities of phosphate through various industrial technologies. At the onset of this work, the process started with 12 samples of PR, PA, and phosphogypsum (PG) being taken simultaneously from two different Moroccan basins (Ouled Abdoun mine represented by K09 and Gantour mine depicted by G10, G20, BG) and various production lines at two processing platforms (Jorf Lasfar and Safi). Afterward, collected samples were prepared and analyzed for REE characterization using an inductively coupled plasma mass spectrometry (ICP-MS). Based on the analysis results, a transfer factor ( TFX) was introduced with the aim of gauging the REE distribution between PA and PG. The results showed that the total concentration of REEs in different phosphate qualities ranged from 411 to 631 ppm; the major part of this concentration was attributed to the four elements: Y, La, Ce, and Nd which constitute more than 77%. The REE distribution between PA and PG depends on neither the phosphate quality nor the industrial technology used since that the distribution results showed that 55 up to 66% of the initial REEs in phosphate rock ended up in the PG. The behavior of each REE was common except for the element scandium, which transferred mainly to the phosphoric acid.

Nov 3, 2021

By J. P. P. Silva

Sodium silicate (water glass) is a modifier reagent widely used in flotation with the function of a depressant or dispersant. The interaction between sodium silicate and mineral surfaces is still not well understood. This investigation aimed to illuminate the sodium silicate action mechanism as a depressant in the flotation of the minerals quartz and calcite. The experiments were done with high-purity mineral samples in the particle size range below 147 µm. The microflotation tests in a modified Hallimond tube showed that, in all systems tested, the efficiency of sodium silicate increased with the concentration. At concentrations above 1,500 g/t, almost total depression (96% for calcite and 97% for quartz) was achieved. The variation of sodium silicate modulus did not alter the quartz flotation performance in the presence of amine (150 g/t). The most efficient depression pH range was observed between 5 and 8. Above pH 10, the depressant action of sodium silicate was negligible. The infrared spectra obtained at pH 7 after silicate contact showed the presence of the groups OH and Si-OH, both suggesting that the adsorption of the neutral species Si(OH)4, as well as siloxane groups (Si-O-Si), attributed to adsorption of polymeric species. Sharing electron pairs is the proposed adsorption mechanism between Si(OH)4 and polymeric species and the surface sites (Si-O on quartz and Ca-O on calcite). At pH 11, the electrostatic repulsion prevents the species adsorption, impairing the sodium silicate action.

When exploration shows a mineral deposit to be of importance, the subsequent work of defining the limits or boundaries of the ore body and preparing it for the extraction of the mineral is termed development (Young, 1946). In underground mining, development also connotes the work that is involved in opening up a deposit preparatory to stoping or productive operations. In this section, mine development is defined to include all studies and operations that will enable a sound evaluation of an explored ore body from the technical and financial standpoints. Though the ultimate objective of all mine development activities is the same, the scope and detail of these activities vary depending on the type of ore body (e.g., flat bodies, lenses and sheets, massive deposits, narrow veins, and bedded deposits), and the method of working the deposit (e.g., under- ground or surface methods or a combination of both of the methods). Therefore, the various contributions in section 3 address such topics as long-range planning, feasibility studies, and valuation for many types of ore bodies and different mining methods. This introductory review is divided into three major parts. In the first part, long-range planning aspects are briefly discussed with .an emphasis on current trends that affect mine planning. In the second part, an overview is provided of the contents in the mine development and valuation section. In the last part, remarks are made on the status, scope, and future of quantitative and computer methods in mine planning and development.

Jan 1, 1979

By R. L. Brown

The Buchans mining district is located roughly at the center of the island of Newfoundland and contains some 18 separate mineral deposits. The first of these deposits was discovered in 1905, the latest discovery having been made in 1979. To the present (1983), some 16 Mt (17.7 million st) grading 1.33% Cu, 7.5% Pb, 14.5% Zn, 115 g/ t (3.7 oz per ton) Ag, and 1.4 g/t (0.04 oz per ton) Au have been mined. Mining operations are now largely terminated, but a few hundred thousand tons of economically marginal reserves may be mined in a salvage operation. The Geological Association of Canada Special Paper No. 22, "The Buchans Orebodies, 50 years of Mining and Exploration," contains papers which describe the history, geology, and the application of evolving geological concepts in exploration. Papers by Neary, Swanson, and Thurlow and Swanson in that volume are topical to the present discussion. Successful exploration techniques at Buchans included physical prospecting, utilization of the state-of-the-art geophysical techniques, saturation diamond drilling which was made possible by the high gross value of the existing ore, and, since 1955, diamond drilling directed by fairly well understood geological parameters. The record of discovery started in 1905 when the Buchans River deposit was found by Matty Mitchell, a prospector employed by the Anglo- Newfoundland Development Co., a British company which owned mineral rights over a very large area in the Red Indian Lake-Exploits River drainage system.

Jan 1, 1991

By G. X. Wang

The nonliving dried water hyacinth (E. crassipes (Mart.) Solms) roots were investigated for biosorption of cadmium and lead and other heavy metal ions in aqueous solutions. Dried water hyacinth roots, when suspended in solution, strongly and rapidly sorb several different metal ions. Factors such as reaction time, pH, initial concentration of metal ions, presence of other metal ions and biomass concentration were investigated. Metal ions, including Cd2+ and Pb2+, were bound to the root in a very pH-dependent manner, with the binding increasing after about pH 3. High levels of removal were obtained. The adsorption was shown to follow the generalized Langmuir adsorption equation. The relative affinity of the roots for lead is greater than for cadmium. The maximum sorptions of the roots were about 33 and 86 mg/g for cadmium and lead, respectively. Only 15-20 minutes were required for the process of uptake onto the biomass to occur. The batch sorption kinetics of the uptake of cadmium and lead can be described by an apparent first-order reversible reaction model. The roots could be regenerated after the metal ions were stripped. A solution of CaCl2 in acidic medium appeared to be the best eluant for desorbing the sequestered Cd and Pb completely at pH 3. The kinetics of the metal stripping process was quite rapid. Successful desorption of Cd and Pb from the biomass by acidic CaCl2 solutions revealed that the metal uptake phenomenon is reversible, implying physical sorption of Cd and Pb.

Jan 1, 1997

By Martín Antonio Encinas‐Romero, Patricia Guerrero‐Germán, Jesús Leobardo Valenzuela‐García, José R. Parga‐Torres, María A. Bracamontes‐Landavazo, Agustín Gómez‐Alvarez

A study was carried out to process a sulfide mineral concentrate from Norwest of Mexico containing 97 g/t Au, 0.15% Cu, and 15% Fe. An oxidative acid pretreatment was investigated using ferric sulfate as oxidant, followed by leaching of gold with sodium cyanide. Scanning electron microscopy, SEM-EDS, and X-ray diffraction, XRD, the analysis confirms the presence of quartz and pyrite species. First, a leaching was carried out without pretreatment, at ambient conditions, T = 25 °C and P = 1 atm, obtaining only a 45.2% gold extraction. Once the presence of Fe and Cu sulfides had been confirmed, the Eh-pH diagrams were constructed for the Fe-S-H2O and Cu-S-H2O systems, where it is appreciated that pyrite and chalcocite can dissolve with high oxidation potentials and forming sulfur, oxidizing to sulfate at highly acidic conditions. The oxidized concentrate was neutralized and adjusted to pH > 10.5; it was leached at ambient conditions, at different particle sizes, 44, 37, and 26.5μm, achieving an Au extraction of 75% using a concentration of 0.5% NaCN, 26.5μm particle size, 20% solids, and P = 1atm. Then the oxidized material was subjected to different temperatures, 25, 50, and 70 °C, under the same conditions and obtaining Au extractions up to 92% at 70°C. Additionally, the leaching process was compared using an autoclave reactor at moderate pressures, obtaining an increase in the extraction of Au up to 98% in 2 h, at T = 70 °C and P = 0.62 MPa.

Jan 23, 2022

By Charles E. Joachim

Current Army tunnel destruction criteria (1) are based on limited nuclear-explosive (NE) and high-explosive (HE) test data. The PILE DRIVER (2) and HARDHAT (3) events investigated tunnel and support system response where yields were relatively large and tunnel diameter small compared to typical underground openings and localized stress fields of low yield weapons. Some limited tunnel destruction information was obtained from underground events of the PLUMBBOB and HARDTACK II Series (4). These events used access drifts which were designed to be self closing at the weapon point. The limited NE data are augmented by HE results from the Underground Explosion Test (UET) Program, a series of model and prototype-scale experiments in granite and sandstone (5). Weapon standoff distances (charge c.g. to tunnel wall) were at or near the maximum for major damage. Limited tunnel destruction was produced by a series of hasty and deliberate tests (6) on abandoned railroad tunnels in basalt. Additional HE data were obtained from model tests at the Waterways Experiment Station (WES) (7) using 2.1 MJ (2 lb) TNT charges and tunnel diameters varying from 3 to 17 cm (1.2 to 6.6 in). Recent laboratory scale HE experiments (8) conducted at the WES under the ESSEX program investigated the effects of tunnel diameter, standoff distance, charge confinement, material strength and to a limited extent, tunnel spacing and liner strength variations on tunnel damage. This paper summarizes the analysis conducted to develop predictions for the effects of low-yield nuclear weapons against tunnels and underground openings in rock.

Jan 1, 1979

By Yongjun Xian

The release of fluid inclusions has a strong potential for the unintentional activation of pyrite during flotation. The present study aims to characterize fluid inclusions in a natural pure pyrite. The results indicate that a certain amount of fluid inclusions exist in the pyrite. The fluid inclusions assume a variety of shapes, including long strips, oval shapes and irregular shapes, with sizes that range from a few microns to dozens of microns. From the EDS results of hollow positions that resulted from the fracture of the fluid inclusions on the pyrite surface, certain amounts of Al, Cr, C, O, Ag and Cu were clearly detected; these elements were not detected in FeS2 pyrite itself. The contents of the inclusions were released into solution when the sample was subjected to a grinding process. Under experimental conditions of 2 g of pyrite cleaned in 40 mL of pure deionized water under an inert atmosphere, the concentrations of Cu, Fe, Cl- and SO4 2- released from the inclusions reached concentrations of 3.29 × 10-6, 32.52 × 10-6, 51.57 × 10-6 and 75.90 × 10-6 mol/L, respectively. These values are significantly greater than those from the experimental nonoxidative and oxidative dissolution of the pyrite. The fluid inclusions of pyrite were, therefore, concluded to represent the dominant sources of Cu, Fe, Cl- and SO4 2- in the aqueous solution. The present investigation provides a new understanding of the source of the unavoidable metal ions in the pulp and may benefit understanding of the flotation theory and environmental geochemistry.

By Libby R. Ricafort, Victorio V. Pato, R. S. Pizarro

Introduction Atlas Consolidated Mining and Development Corp. (ACMDC) started gold production at its Masbate gold mine early in 1980. This involved an open-pit mine and a 3.5-k/d (3850-stpd) carbon-in-pulp processing facility (Pizzaro and Antonio, 1981). When this operation started, the mine began stockpiling sub-grade milling material averaging 1 g/t (0.029 oz per st) gold. Furthermore, geologists estimated that there were additional low grade reserves within the ultimate pit limits. These amounted to 2.4 Mt (2.6 million st) with an average grade of 1.1 g/t (0.03 oz per st) gold. The success of low cost heap leaching prompted an investigation to determine if this tech¬nique would be applicable for the low grade Masbate ore. The findings were favorable and a series of laboratory tests were undertaken. These tests indicated the amenability of this subgrade milling ore to heap leaching. Depending on ore size, gold extractions of more than 60% were obtained. To further define operating parameters for a commercial heap leaching plant, a 400-t (440-st) batch pilot plant was built and operated. These test results were used to design the first commercial heap leaching plant in the Philippines. One design concern was the control of solutions during the rainy season. Due to the material's low grade, every effort was made to minimize capital and operating costs. To this end, surplus mining equipment from the copper operations of ACMDC and used machinery in the crushing circuit were considered. Location: The Masbate gold heap leaching operations are located on the northeastern part of Masbate Island, Philippines. This is about 480 km (300 miles) south-east of Manila. Climate: The climate is moderate with two distinct periods. The dry season runs from January through June, and the rainy season extends from July through December. During the wet season, the rainfall at the mine site averages 300 mm/m (11.8 in. per month) for a total of about 2000 mm/year (78 in. per year). However, heavy downpours in excess of 100 mm/h (4 in. per hour) can occur. Geology: Four distinct rock types have been identified in the pit area. They are tuffaceous agglomerates, andesitic agglomerates, metasedimentary rocks, and hornblende augite andesitic porphyry. The tuffaceous agglomerate occupies the northern and western flanks of the mine. Andesitic agglomerates are localized distinctly in the central portion of the volcanic plug within the mine site. The eastern boundary of the mine is occupied by metasedimentary rocks, whereas, the hornblende augite andesitic porphyry occurs as an intrusive within the andesitic agglomerate and tuffaceous agglomerate. Some areas of the pit contain high proportions of clay minerals, requiring an agglomeration step in the flowsheet. This ensures satisfactory percolation through the heaps. Ore characteristics: Gold and silver are microscopically dis-

Jan 9, 1987

By G. A. Calboreanu

One way of cost reduction is attained when using materials with improved erosion ? corrosion resistance. For many years hard irons successfully answered the Mining Operation needs however application ranges were limited due to the low chemical resistance of such alloys. Corrosion resistance of any hard iron increases when microscopically homogenizing chromium and generating passivation conditions throughout and between all metallographic phases. Chromium distribution of the new material called Max10 was analyzed with EDS ? energy dispersive spectroscopy. At critical depleted chromium carbide ? matrix interfaces chromium increased to 31.72% which is well within passivation levels. Generally the corrosion resistance of high chromium hard irons provided by Metal Casting Industry is limited to 0.5% sulfuric acid and 28 PPM ionic chlorides. Such restrains increased when using Max10 to 2.0% sulfuric acid and 100 PPM ionic chlorides. Max10 contains 35% carbide volume fraction, has excellent corrosion resistance within pH = 1.15 ? 13.6 while fracture toughness under plain - strain conditions and Mode I opening is KIC = 20 KSI.(inch)1/2. Wear rate was calculated with the pin-on-disk apparatus using a diamond indenter per ASTM G99 recommendation. After years of research, experimentation and implementation the Max10 castings were service installed in slurry pumps and mixing equipment. In some applications the life time of slurry pumps manufactured in Max10 tripled versus previously used materials.

Jan 1, 2012

By J. A. Brierley, S. N. McIntosh, C. L. Brierley, E. G. Baglin, E. G. Noble, D. L. Lampshire

The U.S. Bureau of Mines investigated column bioleaching as a means of recovering manganese from a domestic low-grade oxide ore. Manganese was solubilized from the ore using indigenous heterotrophic microorganisms and molasses as the nutrient source. The effects of medium flow rate, molasses concentration, and frequency of medium replacement on the rate of manganese extraction were examined. Results showed that flow rates between 0.4 and 8.1 L/min/m2 had little impact on manganese extraction, while an increase in the total amount of molasses applied during leaching directly affected the extent and rate of manganese extraction. Manganese extractions of more than 90% were achieved in 12 weeks of bioleaching in column tests using 500 g charges of ore. Sugar utilization by the microorganisms and formation of organic acid metabolites were monitored by high performance liquid chromatography (HPLC). Two methods were evaluated to recover manganese from the sugar- depleted bioleaching medium: (1) adsorption onto weak cation exchange resin, followed by stripping and precipitation techniques; and (2) direct precipitation of the manganese as MnCO, using ammonium carbonate. Both recovery methods removed at least 95% of the solubilized manganese from the medium as a carbonate salt. The stripped molasses medium was replenished with fresh molasses and recycled back through the bioleach column, successfully leaching more manganese.

Jan 1, 1993

By S. G. Mougiakakou

A computerized system (SCAPEVIEWER) based on landscape indices and artificial intelligence techniques is proposed in order to classify landscape images into various categories according to the quality of the pictured scenery. Photographs (totally 108) from various landscapes have been clustered, from seven experts in accordance to the mean estimation of landscape quality, into distinctive (C1), typical or common (C2), and indistinctive (C3). For each of the landscape photographs, ten (10) environmental and operational indices have been selected and determined, corresponding to visibility (V), naturalness (N), relief (R), flora quantity (FC), flora quality (F), water (W), skyline (SL), visual entities (G), season (S), and viewer position (P). These landscape indices are fed to a classifier. The classifier is a feed forward Neural Network (NN) trained by a novel hybrid method combining genetic algorithms and the back-propagation algorithm with adaptive learning rate and momentum. A total classification rate of 93.5% has been achieved, using only 8 input neurons. The discarded input neurons correspond to the indices S, and P. The pilot system SCAPEVIEVER has shown the feasibility of landscape photograph classification into three categories (C1, C2, and C3) according to the landscape quality, selecting simultaneously the most robust indices, by means of a computerized system combining the knowledge of an expert with a NN based classifier.

Jan 1, 2003