Re-analysis of archaeobotanical remains from pre- and early agricultural sites provides no evidence for a narrowing of the wild plant food spectrum during the origins of agriculture in southwest Asia

Abstract

Archaeobotanical evidence from southwest Asia is often interpreted as showing that the spectrum of wild plant foods narrowed during the origins of agriculture, but it has long been acknowledged that the recognition of wild plants as foods is problematic. Here, we systematically combine compositional and contextual evidence to recognise the wild plants for which there is strong evidence of their deliberate collection as food at pre-agricultural and early agricultural sites across southwest Asia. Through sample-by-sample analysis of archaeobotanical remains, a robust link is established between the archaeological evidence and its interpretation in terms of food use, which permits a re-evaluation of the evidence for the exploitation of a broad spectrum of wild plant foods at pre-agricultural sites, and the extent to which this changed during the development of early agriculture. Our results show that relatively few of the wild taxa found at pre- and early agricultural sites can be confidently recognised as contributing to the human diet, and we found no evidence for a narrowing of the plant food spectrum during the adoption of agriculture. This has implications for how we understand the processes leading to the domestication of crops, and points towards a mutualistic relationship between people and plants as a driving force during the development of agriculture.

Keywords: Archaeobotany; Broad spectrum; Neolithic; Pre-Pottery Neolithic; Wild plant foods; Wild plants.

Fig. 1

Map of the Pre-Pottery Neolithic sites in southwest Asia with archaeobotanical remains included in the database. Black symbols indicate sites for which sample-level data was available; white symbols indicate sites for which sample-level data was unavailable. Central Anatolian sites—1: Hacılar, 2: Erbaba, 3: Çatalhöyük East, 4: Can Hasan III and 5: Aşikli Höyük. Cypriot sites—6: Mylouthkia, 7: Ais Yiorkis and 8: Kastros. Southern Levantine sites—9: Hayonim Cave, 10: Yiftahel, 11: Nahal Oren, 12: Kebara Cave, 13: Atlit-Yam, 14: Gilgal, 15: Netiv Hagdud, 16: Jericho, 17: Nahal Hemar, 18: Wadi Faynan 16, 19: Shkarat Msaied, 20: Beidha, 21: Ayn Abu Nukhayla, 22: Tell Ramad, 23: Gesher Benot Yaaqov, 24: Ohalo II, 25: Gesher, 26: Wadi al-Hammeh 27, 27: Iraq ed-Dubb, 28: Ain Ghazal, 29: Wadi el-Jilat 13, 30: Wadi el-Jilat 6 & 7, 31: Zahrat adh-Dhra 2, 32: el-Hemmeh, 33: Wadi Fidan A, 34: Wadi Fidan C, 35: Basta I, 36: Tell Ghoraifé, 37: Tell Aswad, 38: Dhuweilla and 39: Azraq 31. Northern Levantine sites—40: Tell Ain el-Kerkh, 41: Tell Ras Shamra, 42: Tell Qaramel, 43: Tell Abr, 44: Dj’ade, 45: Halula, 46: Jerf el Ahmar, 47: Mureybet, 48: Abu Hureyra, 49: Douara Cave, 50: Cafer Höyük, 51: Gritille, 52: Nevali Çori, 53: Göbekli Tepe, 54: Tell Sabi Abyad II, 55: El Kowm I & II, 56: Çayönü and 57: Tell Bouqras. Sites of the eastern Fertile Crescent—58: Hallan Çemi, 59: Demirkoy, 60: Kortik Tepe, 61: Tell Maghzaliyeh, 62: Qermez Dere, 63: Yarym Tepe, 64: Nemrik 9, 65: Mlefaat, 66: Jarmo, 67: Chogha Golan, 68: Sheikh-e Abad, 69: Chia Sabz, 70: Tepe Ali Kosh, 71: Ganj Dareh Tepe, 72: Tepe Abdul Hosein and 73: Chogha Bonut

Fig. 2

Counts of plant items in archaeobotanical samples plotted on a logarithmic scale against Simpson index. a All samples; b samples coded by DC score (small and mixed samples—see ESM Equation A—not plotted). The approximate location of the plant remains from square F78c, Floor II, Hut 1 at Ohalo II is plotted as an asterisk in b

Fig. 3

Counts of plant items in archaeobotanical samples plotted on a logarithmic scale against Simpson index (small and mixed samples—see ESM Equation A—not plotted). Red (filled) symbols indicate samples from the following context categories: a containers; b burnt destruction deposits; c refuse deposits; d external burnt areas; e internal fire installations; f pits. Contour lines indicate density estimations for each context category; multiple lines indicate increasing concentrations of samples