This paper describes the relationship between spectral resolution and classification accuracy in analyses of hyperspectral imaging data acquired from crop leaves. The main scope is to discuss and reduce the risk of model over-fitting. Over-fitting of a classification model occurs when too many and/or irrelevant model terms are included (i.e., a large number of spectral bands), and it may lead to low robustness/repeatability when the classification model is applied to independent validation data. We outline a simple way to quantify the level of model over-fitting by comparing the observed classification accuracies with those obtained from explanatory random data. Hyperspectral imaging data were acquired from two crop-insect pest systems: (1) potato psyllid (Bactericera cockerelli) infestations of individual bell pepper plants (Capsicum annuum) with the acquisition of hyperspectral imaging data under controlled-light conditions (data set 1), and (2) sugarcane borer (Diatraea saccharalis) infestations of individual maize plants (Zea mays) with the acquisition of hyperspectral imaging data from the same plants under two markedly different image-acquisition conditions (data sets 2a and b). For each data set, reflectance data were analyzed based on seven spectral resolutions by dividing 160 spectral bands from 405 to 907 nm into 4, 16, 32, 40, 53, 80, or 160 bands. In the two data sets, similar classification results were obtained with spectral resolutions ranging from 3.1 to 12.6 nm. Thus, the size of the initial input data could be reduced fourfold with only a negligible loss of classification accuracy. In the analysis of data set 1, several validation approaches all demonstrated consistently that insect-induced stress could be accurately detected and that therefore there was little indication of model over-fitting. In the analyses of data set 2, inconsistent validation results were obtained and the observed classification accuracy (81.06%) was only a few percentage points above that obtained using random data (66.7-77.4%). Thus, our analysis highlights a potential risk of model over-fitting and emphasizes the importance of testing for this important aspect as part of developing reliable and robust classification models.

We studied a population of Liriomyza sativae Blanchard (Diptera: Agromyzidae) identified by morphological and molecular techniques from the semiarid region of the Brazilian northeast. The influence of temperature and relative humidity on the survival and reproductive parameters of L. sativae in cowpeas (Vigna unguiculata L. Walp.) (Fabales: Fabaceae) was evaluated. We used temperatures of 18, 20, 22, 25, 28, 30, and 32 +/- 1 degrees C (50 +/- 10% RH) and relative humidity values of 30, 50, 70, and 90 +/- 10% (25 +/- 1 degrees C) under a 14 L:10 D photoperiod. Adult longevity decreased as temperature and relative humidity increased and was greater, in general, for females. The preoviposition and oviposition periods also decreased as temperature increased, whereas relative humidity only caused reductions in the oviposition period at higher levels. Fecundity was similar in the range from 18 to 30 degrees C but decreased at 32 degrees C with respect to relative humidity; the best performances of L. sativae occurred at lower levels. The pattern of oviposition rate changed with temperature and relative humidity. Regardless of temperature and relative humidity, L. sativae laid between 75 and 92% of its eggs on the adaxial surface of the cowpea leaves. This information will be highly useful to design a leafminer production system aimed at the multiplication of natural enemies, as well as for pest management in the field.

-This research aimed to study the infl uence of temperature and relative-humidity (RH) on the development of Liriomyza sativae Blanchard during the egg-adult period, in cowpea, to provide essential information for future biological control projects against the pest. An inverse relation was observed between temperature increase in the range from 15°C to 32°C and development duration. Larval survival was not affected in the temperature range studied, while a high mortality of pupae was observed at 32°C (59.9%). RH did not affect the development time of the immature stages, although it infl uenced their survival. The lower developmental temperature threshold obtained for the egg-adult period was low (7.3°C) when compared with other species of Liriomyza, and was rather low for the larval stage (3.4°C). Based on the thermal requirements for L. sativae, it was possible to estimate the occurrence of 24.5 annual generations at a melon producing region in state of Rio Grande do Norte, Brazil. For laboratory rearing aimed at biological control pest programs, the best rearing conditions are 30°C and 50% RH for the larval stage and 90% RH for the pupal stage.KEY WORDS: Leaf miner, abiotic factor, thermal requirement, biology, molecular characterization RESUMO -A pesquisa teve como objetivo estudar a infl uência da temperatura e da umidade relativa do ar (UR) no desenvolvimento de Liriomyza sativae Blanchard, durante o período ovo-adulto, em feijão caupi, para fornecer subsídios a futuros projetos de controle biológico da praga. Verifi cou-se uma relação inversa entre o aumento da temperatura na faixa de 15°C a 32°C e a duração do desenvolvimento. A sobrevivência larval não foi afetada na faixa térmica estudada, enquanto a 32°C houve alta mortalidade de pupas (59,9%). A UR não afetou a duração dos estágios imaturos, embora tenha infl uenciado a sua sobrevivência. O limiar térmico inferior de desenvolvimento obtido para o período ovo-adulto foi baixo (7,3°C), se comparado a outras espécies de Liriomyza, e bastante reduzido para a fase larval (3,4°C). De acordo com as exigências térmicas constatadas para L. sativae foi possível estimar a ocorrência de 24,5 gerações anuais na região produtora de melão, em Mossoró, RN. Para criações de laboratório, visando à implementação de programas de controle biológico da praga, as melhores condições são temperatura de 30°C e UR de 50% para a fase de larva e 90% para o estágio de pupa de L. sativae.

No abstract

No abstract