Orientador: Gener Tadeu Pereira / Resumo: A cana-de-açúcar é uma das culturas mais expressivas do mercado agrícola nacional. Visando um aumento de produtividade e qualidade da matéria prima, técnicas como a de manejo localizado, que já vem sendo adotada há muitos anos pelas usinas, porém, ainda de forma manual. O objetivo desse trabalho é determinar ambientes de manejo de cana-de-açúcar utilizando quantidade reduzida de variáveis de baixo custo, por meio de técnica de aprendizagem de máquina. Para atingir a máxima eficiência na predição, os dados foram submetidos à estatística descritiva, em seguida, à seleção de regressão “stepwise” para determinar quais variáveis seriam úteis ao modelo. Em seguida foi aplicado teste de multicolinearidade e, por fim, a árvore de decisão classificatória. Para avaliar a eficiência do modelo foi preparada uma matriz de confusão. Foi detectado que as variáveis ligadas às características de formação do solo foram as escolhidas para determinar os ambientes de produção, dando destaque a variável areia. A técnica de regressão “stepwise” mostrou-se eficiente na seleção de variáveis e a árvore de decisão mostrou eficiência na determinação dos ambientes, obtendo a satisfatória acurácia de 75%, além de ter gerado ambientes de manejo mais contínuos na área de cultivo. / Abstract: Sugar cane is one of the most significant crops in the national agricultural market. Aiming to increase the quality and quality of the raw material, techniques such as localized management, which has been adopted for many years by the plants, but still manually. The objective of this work is to determine the sugarcane management environments, using the reduced number of low-cost variables, through the machine learning technique. To achieve maximum prediction efficiency, the data were subjected to descriptive statistics, followed by stepwise regression selection to determine useful variable variables useful in the model. Then, the multicollinearity test was applied and, finally, a classification decision tree. To evaluate the efficiency of the model, a confusion matrix was prepared. It was detected that the variables selected to the soil characteristics were chosen to determine the production environments, highlighting a sand variable. A stepwise regression technique was efficient in the selection of variables and a reduced decision tree in the determination of environments, obtaining a satisfactory satisfaction of 75%, besides showing more continuous management environments in the cultivation area. / Mestre

Thesis (M.Sc. Agric (Soil Science)) -- University of Limpopo, 2013 / Knowledge and management of soil pH, particularly soil acidity across spatially variable soils is important, although this is greatly ignored by farmers in the Limpopo Province of South Africa. The significance of understanding spatial variability of soil acidity is the implementation of best and site-specific management strategies because when soil acidity is poorly managed, toxicity and nutrient deficiency problems in the soil are inevitable. The objective of the study was to evaluate in-field spatial variability of soil pH, and compare the efficiency of managing soil pH through site-specific method vs. uniform lime application. The study was conducted in 3 site years (23o50’ S; 29 o40’ E and 23o59’ S and 28o52’ E) with site year I, and II adjacent to each other in the semi-arid regions of the Limpopo Province, South Africa. Soil samples were taken in four replicates within a 1 m radius from geo-referenced locations in 3 study sites to sampling depths of 0-20 cm on a regular grid of 30m using differential Global Positioning System (DGPS). Soils were analyzed for pH, and SMP buffer pH for lime recommendations. Lime requirement to achieve a soil pH of 6.5 for a 20 cm plough layer per hectare was calculated using CalciumCarbonateequivalent, efficiency factor (fineness factor), and neutralizing index of the liming materials. The spatial maps for SMP buffer pH and lime requirement maps were produced with surfer version 8.0 (Surfer Version 8, Golden Software, Golden, CO). The soil pH datasets from systematic unaligned randomly sampled soils on a 30-m grid were interpolated using inverse distance weighing (IDW) in Surfer software version 8.0 (Surfer Version 8, Golden Software, Golden, CO). Soil pH varied from strongly acidic to slightly acidic with minimum values of 4.22, 3.93, and 4.74 and maximum values of 6.11, 7.00, and 6.82 in site I, II, and II respectively. In Site I, II, and III, the areas of the field that had soil pH values of less than 6.0 were 99.43, 82.61, and 62.89% of the field. When lime was recommended for application using a conventional method of uniform lime application based on an average value derived from samples collected in the whole field, the results of the study showed a waste of lime in excess of lime recommended for individual grids. An excess amount of lime as high as 10, 30, and 7 tons/ha recommended on sites I, II and III respectively under uniform application. These recommendations were in excess on field areas that needed little or no lime applications. Again, the fields showed under applications of lime as much as 30, 35, and 13 tons/ha in site I, II, and III respectively for uniform liming applications. This under- and over recommendations of lime based on average soil pH values suggests that uniform soil acidity management strategy is not an appropriate strategy to be adopted in these fields. Again, in both of these sites as shown in the maps, the areas that required high amount of lime and those that require little or no lime are clearly defined, such that the fields can be divided into lime application zones. When a field is divided into lime application zones, management of soil acidity becomes easier because instead of applying variable rates of lime for every grid, lime rates are applied per zone. These zones could be areas in a field that require, (i) high rates of lime, (ii) low rates of lime, and (iii) areas that requires no lime at all. Agricultural fields that exhibit spatial variability of soil acidity must not be managed or treated as uniform when lime is applied in the field. Keywords: Lime requirement, Site specific management and Soil pH.

Nitrogen (N) is a key nutrient input to crops and one of the major pollutants to the environment from agriculture in the United States. Recent developments in site-specific management (SSM) technology have the potential to reduce both N overapplication and underapplication and increase farmers' net returns. In Virginia, due to the high variability of within-field yield-limiting factors such as soil physical properties and fertility, the adoption of SSM is hindered by high gridsampling cost. Many Virginia corn-wheat-soybean farms have practiced generating yield maps using yield monitors for several years even though few variable applications based on yield maps were reported. It is unknown if the information generated by yield monitors under actual production situations can be used to direct N management for increased net returns in this area. The overall objective of the study is to analyze the economic and environmental impact of alternative management strategies for N in corn and wheat production based on site-specific information in eastern Virginia. Specifically, evaluations were made of three levels of site-specific information regarding crop N requirements combined with variable and uniform N application. The three levels of information are information about the yield potential of the predominant soil type within the field, information about yield potentials of all soils within the field (soil zones), information about yield potentials of smaller sub-field units which are aggregated into functional zones. Effects of information on expected net returns and net N (applied N that is not removed by the crop) were evaluated for corn-wheat-soybean fields in eastern Virginia. Ex post and ex ante evaluations of information were carried out. Historical weather data and farm-level yield data were used to generate yield sequences for individual fields. A Markov chain model was used to describe both temporal and spatial yield variation. Soil maps were used to divide a field into several soil management units. Cluster analysis was used to group subfield units into functional zones based on yield monitor data. Yield monitor data were used to evaluate ex post information and variable application values for 1995-1999, and ex ante information and variable application values for 1999. Ex post analysis results show that soil zone information increased N input but decreased net return, while functional zone information decreased N input and increased net returns. Variable application decreased N input compared with uniform application. Variable application based on soil zone information reduced net return due to cost of overapplication or underapplication. Variable application based on functional information increased net return. Ex ante results show that information on spatial variability was not able to increase farmers?net return due to the cost of variable N application and information. Variable rate application decreases N input relative to uniform application. However, imprecision in the spatial predictor makes the variable application unprofitable due to an imbalance between costs of under- and over-application of N. Sensitivity analysis showed that value of information was positive when temporal uncertainty was eliminated. The ex post results of this study suggest there is potential to improve efficiency of N use and farmers?net returns with site specific management techniques. The ex ante results suggest that site specific management improvements should be tested under conditions faced by farmers including imperfect information about temporal and spatial yield variability. / Ph. D.

This study evaluated the applicability of remote sensing instrumentation for site- specific management of abiotic and biotic stress on cotton grown under a center pivot. Three different irrigation regimes (100%, 75%, and 50% ETc) were imposed on a cotton field to 1) monitor canopy temperatures of cotton with infrared thermometers (IRTs) in order to pinpoint areas of biotic and abiotic stress, 2) compare aerial infrared photography to IRTs mounted on center pivots to correlate areas of biotic and abiotic stress, and 3) relate yield to canopy temperatures. Pivot-mounted IRTs and IR camera were able to differentiate water stress between the irrigation regimes, however, only the IR camera was effectively able to distinguish between biotic (cotton root rot) and abiotic (drought) stress with the assistance of groundtruthing. The 50% ETc regime had significantly higher canopy temperatures, which were reflected in significantly lower lint yields when compared to the 75% and 100% ETc regimes. Deficit irrigation up to 75% ETc had no impact on yield, indicating that water savings were possible without yield depletion.

This study evaluated the applicability of remote sensing instrumentation for site- specific management of abiotic and biotic stress on cotton grown under a center pivot. Three different irrigation regimes (100%, 75%, and 50% ETc) were imposed on a cotton field to 1) monitor canopy temperatures of cotton with infrared thermometers (IRTs) in order to pinpoint areas of biotic and abiotic stress, 2) compare aerial infrared photography to IRTs mounted on center pivots to correlate areas of biotic and abiotic stress, and 3) relate yield to canopy temperatures. Pivot-mounted IRTs and IR camera were able to differentiate water stress between the irrigation regimes, however, only the IR camera was effectively able to distinguish between biotic (cotton root rot) and abiotic (drought) stress with the assistance of groundtruthing. The 50% ETc regime had significantly higher canopy temperatures, which were reflected in significantly lower lint yields when compared to the 75% and 100% ETc regimes. Deficit irrigation up to 75% ETc had no impact on yield, indicating that water savings were possible without yield depletion.

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Precision agriculture (PA) is based on site-specific interventions, according to the spatial variability of productive factors. This strategy tends to decrease the spatial variability of yield in relation to that obtained with the uniform management and optimize the resources used. The objective of this study was to assess the population of corn plants using as a parameter, management zones. Thus, the work was composed of two experiments conducted in different locations and crop years, the municipality of Non-Touch-Me-RS, and experimental areas close together. In experiment 1 (A), conducted in 2009/2010, management zones were delineated through knowledge of the production history through observations of the farmer, separating the plot of study in areas of low (ZB), medium (ZM ) and high productivity (ZA). As for the second experiment (B) in 2010/2011 harvest yield maps standard nine (seven + two crops of soybeans, maize) were superimposed generating three management zones. The areas were classified as presenting relative productivity ZB <95% of the average productivity of the crop, ZM between 95-105 and ZA > 105%. The experiment was a factorial with five seeding rates ranging from 50,000 to 90,000 seeds ha-1 consists of three management zones (ZB, ZM and ZA) under Oxisol. For the second experiment, was added as an assessment of the effect of setting the maize population management zones and their relation to the demand of N by the crop, using as parameter the readings with chlorophyll and N in dry matter in full bloom culture. In both experiments, the maize population was related to productivity in the areas of management, with a correlation coefficient of 0.89 (p> 0.0004), 0.81 (p> 0.0002), 0.97 (p > 0.0002) for ZB, ZM and ZA, respectively. The adjustment of the population of maize plants, parts management provided increases in productivity as compared with the fixed population (70,000 plants ha-1). This increase in ZB due to reduction of the population, Mg is 1.20 h -1 and 1.90 h-1 Mg, resulting in increased economic 19.8 and 28.7% for (A) and (B ), respectively. In the ZA, due to increased population, increased production was 0.89 Mg ha-1 and 0.94 Mg ha-1 providing an economic growth of 5.6 and 6.6% for (A) and (B ), respectively. Evaluations of N in the second experiment, the population growth of maize ZB caused a decrease of 49% for the evaluation of chlorophyll and 44% for N absorbed compared to ZA. However the adjustment of the maize population led to a better use of N fertilizer, and the increase in N uptake by corn of 8.40 and 15% in ZA and ZB when compared to fixed population of 70,000 plants ha-1. / A agricultura de precisão (AP) baseia-se em intervenções sitio-especifico, de acordo com a variabilidade espacial dos fatores produtivos. Essa estratégia tende a diminuir a variabilidade espacial da produtividade em relação ao obtido com o manejo uniforme e otimiza os recursos utilizados. O objetivo deste trabalho foi avaliar o ajuste da população de plantas de milho utilizando como parâmetro, zonas de manejo. Para tanto, o trabalho foi composto por dois experimentos conduzidos em locais e anos agrícolas distintos, no município de Não-Me-Toque-RS, sendo as áreas experimentais próximas entre si. No experimento 1 (A), conduzido na safra 2009/2010, as zonas de manejo foram delimitadas através do conhecimento do histórico de produção através de observações do produtor rural, separando o talhão de estudo em zonas de baixa (ZB), média (ZM) e alta produtividade (ZA). Já para o segundo experimento (B), na safra 2010/2011 nove mapas de produtividade normalizados (sete safras de soja + duas de milho) foram sobrepostos gerando três zonas de manejo. As zonas foram classificadas em ZB apresentando produtividade relativa < 95% da produtividade média da lavoura, ZM entre 95-105 e ZA > 105%. O experimento foi um bifatorial com cinco taxas de semeadura variando de 50.000 a 90.000 sementes ha-1 constituído de três zonas de manejo (ZB, ZM e ZA) sob Latossolo Vermelho Distrófico típico. Para o segundo experimento, acrescentou-se como avaliação o efeito do ajuste da população de milho às zonas de manejo e sua relação com a demanda de N pela cultura, utilizando-se como parâmetro as leituras com clorofilômetro e N na massa seca na floração plena da cultura. Em ambos experimentos, a população de milho foi relacionada com a produtividade nas zonas de manejo, com coeficiente de correlação de 0,89 (p>0,0004); 0,81 (p>0,0002); 0,97 (p>0,0002), para ZB, ZM e ZA, respectivamente. O ajuste da população de plantas de milho às zonas de manejo proporcionou incrementos na produtividade quando comparada com a população fixa (70.000 plantas ha-1). Esse incremento na ZB, devido a redução da população, foi de 1,20 Mg ha-1 e 1,90 Mg ha-1, resultando em incremento econômico de 19,8 e 28,7% para (A) e para (B), respectivamente. Já na ZA, devido ao incremento da população, o incremento produtivo foi de 0,89 Mg ha-1 e 0,94 Mg ha-1 proporcionando um incremento econômico de 5,6 e 6,6% para (A) e (B), respectivamente. Para as avaliações de N no segundo experimento o aumento da população de milho na ZB ocasionou um decréscimo de 49% para as avaliações de clorofilômetro e 44% para o N absorvido quando comparado a ZA. No entanto o ajuste da população de milho ocasionou um melhor aproveitamento do N fertilizante, sendo o incremento do N absorvido pelo milho de 8,40 e 15% nas ZB e ZA quando comparado a população fixa de 70.000 plantas ha-1.

The irrigated rice is common and important to the agricultural scenario of RS, however the spatial variability and low fertility of soils associated with some difficult weed control in this crop provided the use of crop rotation practices with soybean. The rotation with soybean can increase the production and to improve the soil fertility by fertility maps, fertility adjustment in site specific and others sustainable practices of the precision agriculture, therefore, equalizing the costs and expanding the profitability. The objective of this study was to evaluate the technical and economic efficiency of the site specific fertilization in the crop rotation between irrigated rice and soybean. The study was conducted in the farm Formosa Agropecuária, in São Gabriel - RS, during three years. In 2009 was determined the edge of the field with the navigation GPS and, following a grid sampling of 1 ha, was evaluated the soil variability. The fertility maps were made by CR Campeiro 7.0® software, and after this, the field was divided in two plots, the first with precision agriculture practices and the other kept the conventional management. The adjust of fertility in site specific was through of the maps of nitrogen, phosphorus and potassium. The new sampling of soil in 2012, following a grid sampling of 1 ha, allowed identify the exportation of nutrients and to evaluate the fertility strategy and recommendation. In the years 2010 and 2011 by the SMS Ag Leader® software was made the maps of productivity, increasing the rice productivity in 3% in 2010 and 2,2% in 2012, besides 13% more in soybean productivity in 2011. These increases mean approximately U$ 225.00 per hectare. The use of precision agriculture techniques improves the soil fertility, identifying the spatial variability of soil resulting in a rise of production in the rotation between irrigated rice and soybean, specially by the maps of variation of nitrogen in rice. The cost of production was biggest with precision agriculture practices, but the relationship between benefits and cost was positive to this technology. Precision agriculture is practicable technical and economically in lowland. / A lavoura de arroz irrigado do RS tem grande importância no cenário agrícola, porém a alta variabilidade do solo, a baixa fertilidade e ocorrência de invasoras como o arroz vermelho prejudicam esta cultura. A rotação de culturas com a soja vem auxiliar no controle de plantas e no aumento da fertilidade, porém, ainda não é suficiente para alcançar os patamares de produtividade das variedades disponíveis. Assim é necessário ao produtor buscar alternativas para aumentar a produtividade e lucratividade, tendo na Agricultura de Precisão (AP) mais uma ferramenta para auxiliar no processo, através dos mapas de fertilidade, a realização das correções localizadas para racionalizar os custos das lavouras tornando o sistema mais sustentável. Com o objetivo de avaliar a eficiência técnica e econômica da taxa variável de aplicação na cultura do arroz irrigado e da soja, foi desenvolvido o trabalho no município de São Gabriel na propriedade Formosa Agropecuária, por um período de três anos. Inicialmente em 2009 a área foi vetorizada com GPS de navegação e estabelecido uma malha de coleta com grid de 1,0 ha, para avaliar a variabilidade química do solo. Foi utilizado o software CR Campeiro 7 para gerar os mapas de atributos químicos. A partir destes resultados a área foi dividida em dois talhões, um deles para o uso das técnicas de AP, e o outro para o manejo habitual da lavoura. Foram gerados mapas de aplicação à taxa variável de N, P e K para a área destinada a AP. Os mapas de fertilidade foram repetidos em 2012, através de novas coletas de solo nos mesmos pontos, para verificar os efeitos das correções e das exportações de nutrientes. Foram gerados mapas de produtividade nos anos de 2010 e 2011 com o auxilio do software SMS Ag Leader para avaliação. Nas avaliações de produtividade, tivemos um resultado positivo de produção na safra 2010 de 3% no arroz, 2011 de 13% na soja e 2012 de 2,2% novamente no arroz, estas diferenças corresponderam a incremento financeiro nas safras de R$ 489,15 ha-1. A utilização da AP proporcionou além de aumento de produtividade, uma redução da diferença de fertilidade entre as áreas. A utilização das técnicas de mapeamento de AP foi eficiente para identificação da variabilidade do solo. A adubação variável proporcionou aumento de produção, com destaque para o N variável, com maior correlação positiva com a produção. O uso da técnica aumentou o custo total de produção, porém melhorou o custo benefício do investimento realizado por unidade de produção. O balanço de nutrientes foi negativo para K devido à retirada da palha do arroz. A utilização de AP foi favorável, técnica e economicamente a lavoura de várzea.

There are basically two approaches for variable rate of nitrogen prescription, the first one based on management zones (predictive) and the second one based on remote sensing (reactive). These approaches have complementary characteristics and when they are integrated can result in a more efficient N prescription. The main of this study was to delimitate management zones with different nitrogen responses in relation to the nitrogen fertilization and then to compare the different strategies for N prescription, including approaches based on management zones, remote sensing and the integration of both. Management zones were delineated using yield maps, topographic features and soil apparent electric conductivity and were classified as low, medium and high yield potential zone. There was significant interaction between nitrogen rates and management zones for N uptake (p<0.05) and for grain yield (p<0.05). The low yield potential zone showed the highest limitation in relation to nitrogen response. The strategy integrating management zones and remote crop sensing was the one that showed the highest grain yield and economic return for both investigated areas. Fine-tuning of variable rate of nitrogen in wheat by combining crop remote sensing and management zones approaches is a promising tool for precision agriculture in southern Brazil. / Existem basicamente duas abordagens para a prescrição da taxa variável de nitrogênio, a primeira baseada em zonas de manejo (preditivas) e a segunda baseada em sensoriamento remoto (reativas). Essas abordagens possuem características complementares e quando integradas podem resultar em uma prescrição de N mais eficiente. O objetivo desse estudo foi a delimitação de zonas de manejo com diferentes respostas a fertilização nitrogenada e a comparação diferentes estratégias para prescrição de nitrogênio, incluindo abordagens baseadas em sensores de cultura, zonas de manejo e integração de ambas. As zonas de manejo foram delimitadas usando mapas de produtividade, atributos topográficos e condutividade elétrica aparente do solo e foram classificadas em zonas de alto, médio e baixo potencial produtivo. Houve interação significativa entre doses de N e zonas de manejo para a absorção de N (p<0.05) e para a produtividade de grãos (p<0.05), sendo que a zona de baixo potencial produtivo apresentou as maiores limitações quanto a resposta ao fertilizante nitrogenado. A estratégia integrando zonas de manejo e sensoriamento remoto foi a que apresentou as maiores produtividades e maiores retornos econômicos para as duas áreas experimentais. O ajuste fino da taxa variável de nitrogênio em trigo baseada em uma abordagem combinando sensoriamento remoto e zonas de manejo é uma ferramenta promissora para agricultura de precisão na região sul do Brasil.

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / This research aim to evaluate the efficiency of variable fertilizer rate in croplands under precision agriculture (PA) in Rio Grande do Sul State with different level of technologies adoption. In the first chapter was evaluated the PF performance in a small farm with 19 ha in which was cropped soybean in 2005/06 and 2006/07 located in central of Rio Grande do Sul State. In this cropland were used the equipments and technology available in this farm. It was determined the spatial variability of soil attributes by grid sampling with 100 x 100 m also the yield map was done by manual sampling of crop and variable fertilizer rates by soil management zones. The PA increased in average 8% the soybean yield.The soil attribute that had better correlation with yield was soil organic matter. The economic analysis show a return of R$ 72,05 ha-1 due inputs save and increase yields. Also, the PA had a 29% increase of fertilizer use efficiency. In the second chapter were evaluated 6 farms totalizing 138 ha of soybean and 96 ha of maize linked to Aquarius Project of PA located in different counties of Alto Jacui, RS. The main activities evaluated were yield map with a Massey Ferguson combine, model MF 34, fertilizer variable rate with centrifuge force distribution Hercules 10.000 from STARA. The average of result shows decrease of 33.1 and 36.8% in fertilizer inputs and increase of 10 and 14% in soybean and maize yields, respectively. The efficiency use of fertilizer was increased in 47.2 and 62.8% allowing a return of R$ 143.34 ha-1 to soybean and R$ 312.44 ha-1 to maize. / Este trabalho teve por objetivo avaliar a eficiência da adubação a taxa variável em áreas manejadas com agricultura de precisão (AP) no Rio Grande do Sul, com diferentes níveis tecnológicos. No capítulo 1 foram analisados 19 ha cultivados com soja nas safras 2005/06 e 2006/07, localizados em uma pequena propriedade no município de Silveira Martins, região central do estado do Rio Grande do Sul. Nessa área foram utilizados os recursos tecnológicos disponíveis na propriedade. Com isso, foram determinadas as variabilidades espaciais dos atributos do solo através de um grid com 100 x 100 m, confeccionados mapas de produtividade de forma manual, aplicados os insumos em diferentes doses por zonas de manejo. O manejo localizado proporcionou uma economia de 17% na quantidade total dos insumos e um aumento de 8% na produtividade da soja, o que representou um retorno financeiro bruto de R$ 72,05 ha-1 e um aumento na eficiência de 29% em relação ao manejo tradicional. No capítulo 2 foram analisados 138 ha com a cultura da soja e 96 ha com a cultura do milho na safra 2006/07, distribuídos em 6 áreas pertencentes a produtores ligados ao Projeto Aquarius de AP e localizadas em diferentes municípios na região do Alto Jacuí RS. A colheita georreferenciada foi realizada com o auxílio de uma colhedora marca Massey Ferguson modelo MF34 e as aplicações, a taxas variáveis de insumos, foram realizadas através do distribuidor centrífugo Hércules 10000, marca Stara. Para realizar a análise da eficiência do uso de fertilizantes foram comparadas as entradas e saídas de fertilizantes e grãos nos talhões com AP, com a estimativa média de entradas e saídas dos talhões com AC que serviram de testemunhas dentro das propriedades correspondentes. Os resultados evidenciam uma redução média de 33,1 e 36,8% no uso dos insumos e um aumento de 10 e 14% no rendimento das culturas da soja e milho, respectivamente. A eficiência do uso de fertilizantes foi incrementada em 47,2 e 55,1% com o uso da AP, quando consideradas as quantidades totais de fertilizantes, passando para 31,3 e 62,8%, quando considerados os recursos financeiros, proporcionando um retorno de R$ 143,34 ha-1 para a cultura da soja e R$ 312,44 ha-1para a cultura do milho.

Dans un environnement de plus en plus instable et incertain, les entreprises en général, n’ont d’autres choix que de rechercher la performance globale et durable qui seule pourrait constituer un facteur de pérennité et un avantage concurrentiel majeur. La performance globale des entreprises agit sur toutes les dimensions du cycle de vie du produit/service : de la conception, à la livraison au consommateur, réduction des coûts pour être en mesure d’offrir le meilleur prix au Client. Cette logistique d’optimisation de bout à bout de la chaîne est devenue, une nécessité vitale pour assurer la pérennité de l’entreprise. Aujourd’hui, les entreprises en général, et les prestataires logistiques en particuliers, sont confrontés à la prise de conscience que la modélisation de leur chaîne logistique doit être revue de façon plus performante et surtout que les impacts de leur activité doivent être pris en compte : intégrer les contraintes environnementales dans la gestion de leurs activités d’approvisionnement, de distribution, de transport, … et en dégager des voies de progrès économique, social et environnemental, va être l’enjeu stratégique de la prochaine décennie.D’où, la nécessité d’adoption d’un management spécifique ayant pour objectif de concilier entre les pratiques classiques d’aboutissement à la performance globale, et des pratiques novatrices et spécifiques qui prônent le développement durable.Notre travail de recherche traitera la problématique suivante : comment réaliser la performance globale des PME du secteur Transport et logistique au Maroc, en adoptant les pratiques de développement durable ? Ainsi, nous traiterons dans ce travail d’un modèle de Management spécifique capable de conduire les prestataires logistiques Marocain à la performance globale, tout en conciliant les différents enjeux financiers, sociaux et environnementaux.A cet effet, nous avons posé une question centrale : à savoir en quoi le développement durable se présente comme une opportunité pour atteindre la performance durable ? / In an environment of increasingly unstable and uncertain, companies in general, have other choices only to search the global and durable performance which only could constitute a factor of sustainability and a major competing advantage. The global performance of companies’ acts on all the dimensions of the cycle of life of the product / service: from design to delivery to the consumer, reducing costs to be able to offer the best price to the customer. This optimization’s logistics endwise of the chain has become a vital necessity for the sustainability of the company.Today, businesses in general and logistics providers in particular, are confronted with the realization that modeling their supply chain needs to be reviewed more efficient and especially that the impacts of their activity must be taken into account : integrating environmental constraints in the management of their supply activities, distribution, transportation, ... and supply, distribution, of transport,… and to release some ways for economic, social and environmental progress, that must be the strategic challenge of the next decade.Hence, the need to adopt a specific management aiming to reconcile classical practices leading to the global performance, and innovative and specific practices that promote on sustainable development.Our research will treat the following problematic: how to realize the global performance of SMEs in the Transportation and Logistics sector in Morocco, by adopting the practices of sustainable development?Thus, we will treat in this work, a model of specific Management able to lead the Moroccan logistics providers to the global performance, while reconciling the various financial, social and environmental challenges For this purpose, we ask a key question: how the sustainable development is presented as an opportunity to achieve sustainable performance?